Large language models (LLMs) often generate convincing, fluent explanations. However, different from humans, they often generate inconsistent explanations on different inputs. For example, an LLM may explain “all birds can fly” when answering the question “Can sparrows fly?” but meanwhile answer “no” to the related question “Can penguins fly?”. Explanations should be consistent across related examples so that they allow humans to simulate the LLM’s decision process on multiple examples. We propose explanation-consistency finetuning (EC-finetuning), a method that adapts LLMs to generate more consistent natural-language explanations on related examples. EC-finetuning involves finetuning LLMs on synthetic data that is carefully constructed to contain consistent explanations. Across a variety of question-answering datasets in various domains, EC-finetuning yields a 10.0% relative explanation consistency improvement on 4 finetuning datasets, and generalizes to 7 out-of-distribution datasets not seen during finetuning (+4.5% relative). We will make our code available for reproducibility.

Large language models (LLMs) acquire substantial knowledge during pretraining but often need adaptation to new contexts, tasks, or domains, typically achieved through fine-tuning or prompting. However, fine-tuning incurs significant training costs, while prompting increases inference overhead. Inspired by fast weight memory, we introduce GenerativeAdapter, an effective and efficient adaptation method that encode test-time context into language model parameters with a single forward pass. GenerativeAdapter augments a frozen pretrained LM with a lightweight adapter generator, trained via self-supervised learning, to produce parameter-efficient adapters. Notably, our generator is general-purpose, i.e., one generator can adapt the corresponding base model for all langauge processing scenarios. We apply GenerativeAdapter to two pretrained LMs (Mistral-7B-Instruct and Llama2-7B-Chat) and evaluate the adapted models across knowledge acquisition from documents, learning from demonstrations, and personalization for users. In StreamingQA, our approach is effective in injecting knowledge into the LM's parameters, achieving a 63.5\% improvement in F1 score over the model with supervised fine-tuning (from $19.5$ to $31.5$) for contexts as long as 32K tokens. In the MetaICL in-context learning evaluation, our method achieves an average accuracy of $44.9$ across 26 tasks, outperforming the base model. On MSC, our method proves to be highly competitive in memorizing user information from conversations with a 4x reduction in computation and memory costs compared to prompting with full conversation history. Overall, GenerativeAdapter provides a viable solution for adapting large LMs to evolving information and providing tailored user experience, while reducing training and inference costs relative to traditional fine-tuning and prompting techniques.

Chung-En Sun, Xiaodong Liu, Weiwei Yang, Tsui-Wei Weng, Hao Cheng, Aidan San, Michel Galley, Jianfeng Gao. Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers). 2025.

Zonglin Yang, Li Dong, Xinya Du, Hao Cheng, Erik Cambria, Xiaodong Liu, Jianfeng Gao, Furu Wei. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers). 2024.

ELECTRA pre-trains language models by detecting tokens in a sequence that have been replaced by an auxiliary model. Although ELECTRA offers a significant boost in efficiency, its potential is constrained by the training cost brought by the auxiliary model. Notably, this model, which is jointly trained with the main model, only serves to assist the training of the main model and is discarded post-training. This results in a substantial amount of training cost being expended in vain. To mitigate this issue, we propose Fast-ELECTRA, which leverages an existing language model as the auxiliary model. To construct a learning curriculum for the main model, we smooth its output distribution via temperature scaling following a descending schedule. Our approach rivals the performance of state-of-the-art ELECTRA-style pre-training methods, while significantly eliminating the computation and memory cost brought by the joint training of the auxiliary model. Our method also reduces the sensitivity to hyper-parameters and enhances the pre-training stability.

In human-written articles, we often leverage the subtleties of text style, such as bold and italics, to guide the attention of readers. These textual emphases are vital for the readers to grasp the conveyed information. When interacting with large language models (LLMs), we have a similar need -- steering the model to pay closer attention to user-specified information, e.g., an instruction. Existing methods, however, are constrained to process plain text and do not support such a mechanism. This motivates us to introduce PASTA -- Post-hoc Attention STeering Approach, a method that allows LLMs to read text with user-specified emphasis marks. To this end, PASTA identifies a small subset of attention heads and applies precise attention reweighting on them, directing the model attention to user-specified parts. Like prompting, PASTA is applied at inference time and does not require changing any model parameters. Experiments demonstrate that PASTA can substantially enhance an LLM's ability to follow user instructions or integrate new knowledge from user inputs, leading to a significant performance improvement on a variety of tasks, e.g., an average accuracy improvement of 22\% for LLAMA-7B. Our code is publicly available at https://github.com/QingruZhang/PASTA .

Linyuan Gong, Chenyan Xiong, Xiaodong Liu, Payal Bajaj, Yiqing Xie, Alvin Cheung, Jianfeng Gao, Xia Song. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Despite the effectiveness of ELECTRA-style pre-training, their performance is dependent on the careful selection of the model size for the auxiliary generator, leading to high trial-and-error costs. In this paper, we present the first systematic study of this problem. Our theoretical investigation highlights the importance of controlling the generator capacity in ELECTRA-style training. Meanwhile, we found it is not handled properly in the original ELECTRA design, leading to the sensitivity issue. Specifically, since adaptive optimizers like Adam will cripple the weighing of individual losses in the joint optimization, the original design fails to control the generator training effectively. To regain control over the generator, we modularize the generator optimization by decoupling the generator optimizer and discriminator optimizer completely, instead of simply relying on the weighted objective combination. Our simple technique reduced the sensitivity of ELECTRA training significantly and obtains considerable performance gain compared to the original design.

Backpropagation, the cornerstone of deep learning, is limited to computing gradients for continuous variables. This limitation poses challenges for problems involving discrete latent variables. To address this issue, we propose a novel approach to approximate the gradient of parameters involved in generating discrete latent variables. First, we examine the widely used Straight-Through (ST) heuristic and demonstrate that it works as a first-order approximation of the gradient. Guided by our findings, we propose ReinMax, which achieves second-order accuracy by integrating Heun’s method, a second-order numerical method for solving ODEs. ReinMax does not require Hessian or other second-order derivatives, thus having negligible computation overheads. Extensive experimental results on various tasks demonstrate the superiority of ReinMax over the state of the art.

Existing large language models (LLMs) can only afford fix-sized inputs due to the input length limit, preventing them from utilizing rich long-context information from past inputs. To address this, we propose a framework, Language Models Augmented with Long-Term Memory (LongMem), which enables LLMs to memorize long history. We design a novel decoupled network architecture with the original backbone LLM frozen as a memory encoder and an adaptive residual side-network as a memory retriever and reader. Such a decoupled memory design can easily cache and update long-term past contexts for memory retrieval without suffering from memory staleness. Enhanced with memory-augmented adaptation training, LongMem can thus memorize long past context and use long-term memory for language modeling. The proposed memory retrieval module can handle unlimited-length context in its memory bank to benefit various downstream tasks. Typically, LongMem can enlarge the long-form memory to 65k tokens and thus cache many-shot extra demonstration examples as long-form memory for in-context learning. Experiments show that our method outperforms strong long-context models on ChapterBreak, a challenging long-context modeling benchmark, and achieves remarkable improvements on memory-augmented in-context learning over LLMs. The results demonstrate that the proposed method is effective in helping language models to memorize and utilize long-form contents.

The retriever-reader framework is popular for open-domain question answering (ODQA) due to its ability to use explicit knowledge.Although prior work has sought to increase the knowledge coverage by incorporating structured knowledge beyond text, accessing heterogeneous knowledge sources through a unified interface remains an open question.While data-to-text generation has the potential to serve as a universal interface for data and text, its feasibility for downstream tasks remains largely unknown.In this work, we bridge this gap and use the data-to-text method as a means for encoding structured knowledge for ODQA.Specifically, we propose a verbalizer-retrieverreader framework for ODQA over data and text where verbalized tables from Wikipedia and graphs from Wikidata are used as augmented knowledge sources.We show that our Unified Data and Text QA, UDT-QA, can effectively benefit from the expanded knowledge index, leading to large gains over textonly baselines.Notably, our approach sets the single-model state-of-the-art on Natural Questions.Furthermore, our analyses indicate that verbalized knowledge is preferred for answer reasoning for both adapted and hot-swap settings.

Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

Most of today's AI systems focus on using self-attention mechanisms and transformer architectures on large amounts of diverse data to achieve impressive performance gains. In this paper, we propose to augment the transformer architecture with an external attention mechanism to bring external knowledge and context to bear. By integrating external information into the prediction process, we hope to reduce the need for ever-larger models and increase the democratization of AI systems. We find that the proposed external attention mechanism can significantly improve the performance of existing AI systems, allowing practitioners to easily customize foundation AI models to many diverse downstream applications. In particular, we focus on the task of Commonsense Reasoning, demonstrating that the proposed external attention mechanism can augment existing transformer models and significantly improve the model's reasoning capabilities. The proposed system, Knowledgeable External Attention for commonsense Reasoning (KEAR), reaches human parity on the open CommonsenseQA research benchmark with an accuracy of 89.4% in comparison to the human accuracy of 88.9%.

Traditional knowledge distillation (KD) methods manually design student architectures to compress large models given pre-specified computational cost. This requires several trials to find viable students, and repeating the process with change in computational budget. We use Neural Architecture Search (NAS) to automatically distill several compressed students with variable cost from a large model. Existing NAS methods train a single SuperLM consisting of millions of subnetworks with weight-sharing, resulting in interference between subnetworks of different sizes. Additionally, many of these works are task-specific requiring task labels for SuperLM training. Our framework AutoDistil addresses above challenges with the following steps: (a) Incorporates inductive bias and heuristics to partition Transformer search space into K compact sub-spaces (e.g., K=3 can generate typical student sizes of base, small and tiny); (b) Trains one SuperLM for each sub-space using task-agnostic objective (e.g., self-attention distillation) with weight-sharing of students; (c) Lightweight search for the optimal student without re-training. Task-agnostic training and search allow students to be reused for fine-tuning on any downstream task. Experiments on GLUE benchmark demonstrate AutoDistil to outperform state-of-the-art KD and NAS methods with upto 3x reduction in computational cost and negligible loss in task performance. Code and model checkpoints are available at https://github.com/microsoft/autodistil.

Pretraining large neural language models, such as BERT, has led to impressive gains on many natural language processing (NLP) tasks. However, most pretraining efforts focus on general domain corpora, such as newswire and Web. A prevailing assumption is that even domain-specific pretraining can benefit by starting from general-domain language models. In this article, we challenge this assumption by showing that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains over continual pretraining of general-domain language models. To facilitate this investigation, we compile a comprehensive biomedical NLP benchmark from publicly available datasets. Our experiments show that domain-specific pretraining serves as a solid foundation for a wide range of biomedical NLP tasks, leading to new state-of-the-art results across the board. Further, in conducting a thorough evaluation of modeling choices, both for pretraining and task-specific fine-tuning, we discover that some common practices are unnecessary with BERT models, such as using complex tagging schemes in named entity recognition. To help accelerate research in biomedical NLP, we have released our state-of-the-art pretrained and task-specific models for the community, and created a leaderboard featuring our BLURB benchmark (short for Biomedical Language Understanding & Reasoning Benchmark) at https://aka.ms/BLURB .

Hao Cheng, Yelong Shen, Xiaodong Liu, Pengcheng He, Weizhu Chen, Jianfeng Gao. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Chen Liang, Simiao Zuo, Minshuo Chen, Haoming Jiang, Xiaodong Liu, Pengcheng He, Tuo Zhao, Weizhu Chen. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Yuning Mao, Pengcheng He, Xiaodong Liu, Yelong Shen, Jianfeng Gao, Jiawei Han, Weizhu Chen. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

This paper examines the challenging problem of learning representations of entities and relations in a complex multi-relational knowledge graph.We propose HittER, a Hierarchical Transformer model to jointly learn Entityrelation composition and Relational contextualization based on a source entity's neighborhood.Our proposed model consists of two different Transformer blocks: the bottom block extracts features of each entity-relation pair in the local neighborhood of the source entity and the top block aggregates the relational information from outputs of the bottom block.We further design a masked entity prediction task to balance information from the relational context and the source entity itself.Experimental results show that HittER achieves new stateof-the-art results on multiple link prediction datasets.We additionally propose a simple approach to integrate HittER into BERT and demonstrate its effectiveness on two Freebase factoid question answering datasets.

Adversarial regularization has been shown to improve the generalization performance of deep learning models in various natural language processing tasks.Existing works usually formulate the method as a zero-sum game, which is solved by alternating gradient descent/ascent algorithms.Such a formulation treats the adversarial and the defending players equally, which is undesirable because only the defending player contributes to the generalization performance.To address this issue, we propose Stackelberg Adversarial Regularization (SALT), which formulates adversarial regularization as a Stackelberg game.This formulation induces a competition between a leader and a follower, where the follower generates perturbations, and the leader trains the model subject to the perturbations.Different from conventional approaches, in SALT, the leader is in an advantageous position.When the leader moves, it recognizes the strategy of the follower and takes the anticipated follower's outcomes into consideration.Such a leader's advantage enables us to improve the model fitting to the unperturbed data.The leader's strategic information is captured by the Stackelberg gradient, which is obtained using an unrolling algorithm.Our experimental results on a set of machine translation and natural language understanding tasks show that SALT outperforms existing adversarial regularization baselines across all tasks.Our code is publicly available.

Hao Cheng, Xiaodong Liu, Lis Pereira, Yaoliang Yu, Jianfeng Gao. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Lis Pereira, Xiaodong Liu, Hao Cheng, Hoifung Poon, Jianfeng Gao, Ichiro Kobayashi. Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2021.

Hyperparameter (HP) tuning in deep learning is an expensive process, prohibitively so for neural networks (NNs) with billions of parameters.We show that, in the recently discovered Maximal Update Parametrization ($\mu$P), many optimal HPs remain stable even as model size changes. This leads to a new HP tuning paradigm we call *$\mu$Transfer*: parametrize the target model in $\mu$P, tune the HP indirectly on a smaller model, and *zero-shot transfer* them to the full-sized model, i.e., without directly tuning the latter at all.We verify $\mu$Transfer on Transformer and ResNet. For example, 1) by transferring pretraining HPs from a model of 13M parameters, we outperform published numbers of BERT-large (350M parameters), with a total tuning cost equivalent to pretraining BERT-large once; 2) by transferring from 40M parameters, we outperform published numbers of the 6.7B GPT-3 model, with tuning cost only 7% of total pretraining cost. A Pytorch implementation of our technique can be found at github.com/microsoft/mup. See arxiv.org for the full, up-to-date version of this work.

Transfer learning has fundamentally changed the landscape of natural language processing (NLP).Many state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks.However, due to limited data resources from downstream tasks and the extremely high complexity of pre-trained models, aggressive fine-tuning often causes the fine-tuned model to overfit the training data of downstream tasks and fail to generalize to unseen data.To address such an issue in a principled manner, we propose a new learning framework for robust and efficient fine-tuning for pre-trained models to attain better generalization performance.The proposed framework contains two important ingredients: 1. Smoothness-inducing regularization, which effectively manages the complexity of the model; 2. Bregman proximal point optimization, which is an instance of trustregion methods and can prevent aggressive updating.Our experiments show that the proposed framework achieves new state-of-the-art performance on a number of NLP tasks including GLUE, SNLI, SciTail and ANLI.Moreover, it also outperforms the state-of-the-art T5 model, which is the largest pre-trained model containing 11 billion parameters, on GLUE. 1

When translating natural language questions into SQL queries to answer questions from a database, contemporary semantic parsing models struggle to generalize to unseen database schemas.The generalization challenge lies in (a) encoding the database relations in an accessible way for the semantic parser, and (b) modeling alignment between database columns and their mentions in a given query.We present a unified framework, based on the relation-aware self-attention mechanism, to address schema encoding, schema linking, and feature representation within a text-to-SQL encoder.On the challenging Spider dataset this framework boosts the exact match accuracy to 57.2%, surpassing its best counterparts by 8.7% absolute improvement.Further augmented with BERT, it achieves the new state-of-the-art performance of 65.6% on the Spider leaderboard.In addition, we observe qualitative improvements in the model's understanding of schema linking and alignment.Our implementation will be open-sourced at https://github.com/Microsoft/rat-sql.

In Text-to-SQL semantic parsing, selecting the correct entities (tables and columns) for the generated SQL query is both crucial and challenging; the parser is required to connect the natural language (NL) question and the SQL query to the structured knowledge in the database.We formulate two linking processes to address this challenge: schema linking which links explicit NL mentions to the database and structural linking which links the entities in the output SQL with their structural relationships in the database schema.Intuitively, the effectiveness of these two linking processes changes based on the entity being generated, thus we propose to dynamically choose between them using a gating mechanism.Integrating the proposed method with two graph neural network-based semantic parsers together with BERT representations demonstrates substantial gains in parsing accuracy on the challenging Spider dataset.Analyses show that our proposed method helps to enhance the structure of the model output when generating complicated SQL queries and offers more explainable predictions.

Transformers have proved effective in many NLP tasks.However, their training requires non-trivial efforts regarding carefully designing cutting-edge optimizers and learning rate schedulers (e.g., conventional SGD fails to train Transformers effectively).Our objective here is to understand what complicates Transformer training from both empirical and theoretical perspectives.Our analysis reveals that unbalanced gradients are not the root cause of the instability of training.Instead, we identify an amplification effect that influences training substantially-for each layer in a multi-layer Transformer model, heavy dependency on its residual branch makes training unstable, since it amplifies small parameter perturbations (e.g., parameter updates) and results in significant disturbances in the model output.Yet we observe that a light dependency limits the model potential and leads to inferior trained models.Inspired by our analysis, we propose Admin (Adaptive model initialization) to stabilize the early stage's training and unleash its full potential in the late stage.Extensive experiments show that Admin is more stable, converges faster, and leads to better performance 1 .W (V 2 ) h , where f s is the row-wise softmax function and W (•) h are parameters.

We propose to pre-train a unified language model for both autoencoding and partially autoregressive language modeling tasks using a novel training procedure, referred to as a pseudo-masked language model (PMLM). Given an input text with masked tokens, we rely on conventional masks to learn inter-relations between corrupted tokens and context via autoencoding, and pseudo masks to learn intra-relations between masked spans via partially autoregressive modeling. With well-designed position embeddings and self-attention masks, the context encodings are reused to avoid redundant computation. Moreover, conventional masks used for autoencoding provide global masking information, so that all the position embeddings are accessible in partially autoregressive language modeling. In addition, the two tasks pre-train a unified language model as a bidirectional encoder and a sequence-to-sequence decoder, respectively. Our experiments show that the unified language models pre-trained using PMLM achieve new state-of-the-art results on a wide range of language understanding and generation tasks across several widely used benchmarks. The code and pre-trained models are available at https://github.com/microsoft/unilm.

In this paper, we present a Multi-Task Deep Neural Network (MT-DNN) for learning representations across multiple natural language understanding (NLU) tasks.MT-DNN not only leverages large amounts of cross-task data, but also benefits from a regularization effect that leads to more general representations to help adapt to new tasks and domains.MT-DNN extends the model proposed in Liu et al. (2015) by incorporating a pre-trained bidirectional transformer language model, known as BERT (Devlin et al., 2018).MT-DNN obtains new state-of-the-art results on ten NLU tasks, including SNLI, SciTail, and eight out of nine GLUE tasks, pushing the GLUE benchmark to 82.7% (2.2% absolute improvement) 1 .We also demonstrate using the SNLI and Sc-iTail datasets that the representations learned by MT-DNN allow domain adaptation with substantially fewer in-domain labels than the pre-trained BERT representations.The code and pre-trained models are publicly available at https://github.com/namisan/mt-dnn. * Equal Contribution. 1 As of February 25, 2019 on the latest GLUE test set.

Lianhui Qin, Michel Galley, Chris Brockett, Xiaodong Liu, Xiang Gao, Bill Dolan, Yejin Choi, Jianfeng Gao. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. 2019.

Intelligent personal assistant systems that are able to have multi-turn conversations with human users are becoming increasingly popular. Most previous research has been focused on using either retrieval-based or generation-based methods to develop such systems. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. However, the performance of the methods is limited by the size of the response repository. On the other hand, generation-based methods can produce highly coherent responses on any topics. But the generated responses are often generic and not informative due to the lack of grounding knowledge. In this paper, we propose a hybrid neural conversation model that combines the merits of both response retrieval and generation methods. Experimental results on Twitter and Foursquare data show that the proposed model outperforms both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model) under both automatic evaluation metrics and human evaluation. We hope that the findings in this study provide new insights on how to integrate text retrieval and text generation models for building conversation systems.

Huazheng Wang, Zhe Gan, Xiaodong Liu, Jingjing Liu, Jianfeng Gao, Hongning Wang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

This paper presents a new Unified pre-trained Language Model (UniLM) that can be fine-tuned for both natural language understanding and generation tasks. The model is pre-trained using three types of language modeling tasks: unidirectional, bidirectional, and sequence-to-sequence prediction. The unified modeling is achieved by employing a shared Transformer network and utilizing specific self-attention masks to control what context the prediction conditions on. UniLM compares favorably with BERT on the GLUE benchmark, and the SQuAD 2.0 and CoQA question answering tasks. Moreover, UniLM achieves new state-of-the-art results on five natural language generation datasets, including improving the CNN/DailyMail abstractive summarization ROUGE-L to 40.51 (2.04 absolute improvement), the Gigaword abstractive summarization ROUGE-L to 35.75 (0.86 absolute improvement), the CoQA generative question answering F1 score to 82.5 (37.1 absolute improvement), the SQuAD question generation BLEU-4 to 22.12 (3.75 absolute improvement), and the DSTC7 document-grounded dialog response generation NIST-4 to 2.67 (human performance is 2.65). The code and pre-trained models are available at https://github.com/microsoft/unilm.

We propose a simple yet robust stochastic answer network (SAN) that simulates multi-step reasoning in machine reading comprehension.Compared to previous work such as ReasoNet which used reinforcement learning to determine the number of steps, the unique feature is the use of a kind of stochastic prediction dropout on the answer module (final layer) of the neural network during the training.We show that this simple trick improves robustness and achieves results competitive to the state-of-the-art on the Stanford Question Answering Dataset (SQuAD), the Adversarial SQuAD, and the Microsoft MAchine Reading COmprehension Dataset (MS MARCO).

We investigate the problem of Language-Based Image Editing (LBIE). Given a source image and a natural language description, we want to generate a target image by editing the source image based on the description. We propose a generic modeling framework for two subtasks of LBIE: language-based image segmentation and image colorization. The framework uses recurrent attentive models to fuse image and language features. Instead of using a fixed step size, we introduce for each region of the image a termination gate to dynamically determine after each inference step whether to continue extrapolating additional information from the textual description. The effectiveness of the framework is validated on three datasets. First, we introduce a synthetic dataset, called CoSaL, to evaluate the end-to-end performance of our LBIE system. Second, we show that the framework leads to state-of-the-art performance on image segmentation on the ReferIt dataset. Third, we present the first language-based colorization result on the Oxford-102 Flowers dataset.

Neural language models (NLMs) have recently gained a renewed interest by achieving state-of-the-art performance across many natural language processing (NLP) tasks. However, NLMs are very computationally demanding largely due to the computational cost of the decoding process, which consists of a softmax layer over a large vocabulary.We observe that in the decoding of many NLP tasks, only the probabilities of the top-K hypotheses need to be calculated preciously and K is often much smaller than the vocabulary size. This paper proposes a novel softmax layer approximation algorithm, called Fast Graph Decoder (FGD), which quickly identifies, for a given context, a set of K words that are most likely to occur according to a NLM. We demonstrate that FGD reduces the decoding time by an order of magnitude while attaining close to the full softmax baseline accuracy on neural machine translation and language modeling tasks. We also prove the theoretical guarantee on the softmax approximation quality.

Reading comprehension (RC) is a challenging task that requires synthesis of information across sentences and multiple turns of reasoning. Using a state-of-the-art RC model, we empirically investigate the performance of single-turn and multiple-turn reasoning on the SQuAD and MS MARCO datasets. The RC model is an end-to-end neural network with iterative attention, and uses reinforcement learning to dynamically control the number of turns. We find that multiple-turn reasoning outperforms single-turn reasoning for all question and answer types; further, we observe that enabling a flexible number of turns generally improves upon a fixed multiple-turn strategy. %across all question types, and is particularly beneficial to questions with lengthy, descriptive answers. We achieve results competitive to the state-of-the-art on these two datasets.

Xiaodong Liu, Jianfeng Gao, Xiaodong He, Li Deng, Kevin Duh, Ye-yi Wang. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2015.

We propose a novel framework for Chinese Spelling Check (CSC), which is an automatic algorithm to detect and correct Chinese spelling errors. Our framework contains two key components: candidate generation and candidate ranking . Our framework differs from previous research, such as Statistical Machine Translation (SMT) based model or Language Model (LM) based model, in that we use both SMT and LM models as components of our framework for generating the correction candidates, in order to obtain maximum recall; to improve the precision, we further employ a Support Vector Machines (SVM) classifier to rank the candidates generated by the SMT and the LM. Experiments show that our framework outperforms other systems, which adopted the same or similar resources as ours in the SIGHAN 7 shared task; even comparing with the state-of-the-art systems, which used more resources, such as a considerable large dictionary, an idiom dictionary and other semantic information, our framework still obtains competitive results. Furthermore, to address the resource scarceness problem for training the SMT model, we generate around 2 million artificial training sentences using the Chinese character confusion sets, which include a set of Chinese characters with similar shapes and similar pronunciations, provided by the SIGHAN 7 shared task.

A machine-readable bilingual dictionary plays a crucial role in many natural language processing tasks, such as statistical machine translation and cross-language information retrieval. In this article, we propose a framework for extracting a bilingual dictionary from comparable corpora by exploiting a novel combination of topic modeling and word aligners such as the IBM models. Using a multilingual topic model, we first convert a comparable document -aligned corpus into a parallel topic -aligned corpus. This novel topic-aligned corpus is similar in structure to the sentence -aligned corpus frequently employed in statistical machine translation and allows us to extract a bilingual dictionary using a word alignment model. The main advantages of our framework is that (1) no seed dictionary is necessary for bootstrapping the process, and (2) multilingual comparable corpora in more than two languages can also be exploited. In our experiments on a large-scale Wikipedia dataset, we demonstrate that our approach can extract higher precision dictionaries compared to previous approaches and that our method improves further as we add more languages to the dataset.