Text-based reinforcement-learning agents improve their policies by interacting with their environments to collect more training data.However, these self-collected data inevitably contain intermediate failed actions caused by attempting physically infeasible behaviors and/or hallucinations.Directly learning a policy from such trajectories can reinforce incorrect behaviors and reduce task success rates.In this paper, we propose a failed action-aware objective that suppresses the negative impact of failed actions during training by assigning zero return based on textual feedback.Building on this objective, we introduce a perturbation method that leverages unsuccessful trajectories to construct new successful ones that share the same goal.This allows agents to benefit from diverse experiences without further interaction with the environment.Experiments in ALFWorld and ScienceWorld demonstrate that our method significantly outperforms strong baselines and generalizes across environments.

To improve user engagement during conversations with dialogue systems, we must improve individual dialogue responses and dialogue impressions such as consistency, personality, and empathy throughout the entire dialogue. While such dialogue systems have been developing rapidly with the help of large language models (LLMs), reinforcement learning from AI feedback (RLAIF) has attracted attention to align LLM-based dialogue models for such dialogue impressions. In RLAIF, a reward model based on another LLM is used to create a training signal for an LLM-based dialogue model using zero-shot/few-shot prompting techniques. However, evaluating an entire dialogue only by prompting LLMs is challenging. In this study, the supervised fine-tuning (SFT) of LLMs prepared reward models corresponding to 12 metrics related to the impression of the entire dialogue for evaluating dialogue responses. We tuned our dialogue models using the reward model signals as feedback to improve the impression of the system. The results of automatic and human evaluations showed that tuning the dialogue model using our reward model corresponding to dialogue impression improved the evaluation of individual metrics and the naturalness of the dialogue response.

FEVEROUS is a benchmark and research initiative focused on fact extraction and verification tasks involving unstructured text and structured tabular data. In FEVEROUS, existing works often rely on extensive preprocessing and utilize rule-based transformations of data, leading to potential context loss or misleading encodings. This paper introduces a simple yet powerful model that nullifies the need for modality conversion, thereby preserving the original evidence’s context. By leveraging pre-trained models on diverse text and tabular datasets and by incorporating a lightweight attention-based mechanism, our approach efficiently exploits latent connections between different data types, thereby yielding comprehensive and reliable verdict predictions. The model’s modular structure adeptly manages multi-modal information, ensuring the integrity and authenticity of the original evidence are uncompromised. Comparative analyses reveal that our approach exhibits competitive performance, aligning itself closely with top-tier models on the FEVEROUS benchmark.

Elastic weight consolidation (EWC, Kirkpatrick et al. 2017) is a promising approach to addressing catastrophic forgetting in sequential training. We find that the effect of EWC can diminish when fine-tuning large-scale pre-trained language models on different datasets. We present two simple objective functions to mitigate this problem by rescaling the components of EWC. Experiments on natural language inference and fact-checking tasks indicate that our methods require much smaller values for the trade-off parameters to achieve results comparable to EWC.

Exploiting sentence-level labels, which are easy to obtain, is one of the plausible methods to improve low-resource named entity recognition (NER), where token-level labels are costly to annotate.Current models for jointly learning sentence and token labeling are limited to binary classification.We present a joint model that supports multi-class classification and introduce a simple variant of self-attention that allows the model to learn scaling factors.Our model produces 3.78%, 4.20%, 2.08% improvements in F1 over the BiLSTM-CRF baseline on e-commerce product titles in three different low-resource languages: Vietnamese, Thai, and Indonesian, respectively.

Bosheng Ding, Linlin Liu, Lidong Bing, Canasai Kruengkrai, Thien Hai Nguyen, Shafiq Joty, Luo Si, Chunyan Miao. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP). 2020.

This paper proposes a novel method for generating compact answers to open-domain why-questions, such as the following answer, “Because deep learning technologies were introduced,” to the question, “Why did Google’s machine translation service improve so drastically?” Although many works have dealt with why-question answering, most have focused on retrieving as answers relatively long text passages that consist of several sentences. Because of their length, such passages are not appropriate to be read aloud by spoken dialog systems and smart speakers; hence, we need to create a method that generates compact answers. We developed a novel neural summarizer for this compact answer generation task. It combines a recurrent neural network-based encoderdecoder model with stacked convolutional neural networks and was designed to effectively exploit background knowledge, in this case a set of causal relations (e.g., “[Microsoft’s machine translation has made great progress over the last few years]effect since [it started to use deep learning.]cause”) that was extracted from a large web data archive (4 billion web pages). Our experimental results show that our method achieved significantly better ROUGE F-scores than existing encoder-decoder models and their variations that were augmented with query-attention and memory networks, which are used to exploit the background knowledge.

We show that sampling latent variables multiple times at a gradient step helps in improving a variational autoencoder and propose a simple and effective method to better exploit these latent variables through hidden state averaging.Consistent gains in performance on two different datasets, Penn Treebank and Yahoo, indicate the generalizability of our method.1

Canasai Kruengkrai. 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 proposes a neural network-based method for generating compact answers to open-domain why-questions (e.g., "Why was Mr. Trump elected as the president of the US?"). Unlike factoid question answering methods that provide short text spans as answers, existing work for why-question answering have aimed at answering questions by retrieving relatively long text passages, each of which often consists of several sentences, from a text archive. While the actual answer to a why-question may be expressed over several consecutive sentences, these often contain redundant and/or unrelated parts. Such answers would not be suitable for spoken dialog systems and smart speakers such as Amazon Echo, which receive much attention in these days. In this work, we aim at generating non-redundant compact answers to why-questions from answer passages retrieved from a very large web data corpora (4 billion web pages) by an already existing open-domain why-question answering system, using a novel neural network obtained by extending existing summarization methods. We also automatically generate training data using a large number of causal relations automatically extracted from 4 billion web pages by an existing supervised causality recognizer. The data is used to train our neural network, together with manually created training data. Through a series of experiments, we show that both our novel neural network and auto-generated training data improve the quality of the generated answers both in ROUGE score and in a subjective evaluation.

We propose a method for recognizing such event causalities as "smoke cigarettes" → "die of lung cancer" using background knowledge taken from web texts as well as original sentences from which candidates for the causalities were extracted. We retrieve texts related to our event causality candidates from four billion web pages by three distinct methods, including a why-question answering system, and feed them to our multi-column convolutional neural networks. This allows us to identify the useful background knowledge scattered in web texts and effectively exploit the identified knowledge to recognize event causalities. We empirically show that the combination of our neural network architecture and background knowledge significantly improves average precision, while the previous state-of-the-art method gains just a small benefit from such background knowledge.

Why-question answering (why-QA) is a task to retrieve answers (or answer passages) to why-questions (e.g., "why are tsunamis generated?") from a text archive. Several previously proposed methods for why-QA improved their performance by automatically recognizing causalities that are expressed with such explicit cues as "because" in answer passages and using the recognized causalities as a clue for finding proper answers. However, in answer passages, causalities might be implicitly expressed, (i.e., without any explicit cues): "An earthquake suddenly displaced sea water and a tsunami was generated." The previous works did not deal with such implicitly expressed causalities and failed to find proper answers that included the causalities. We improve why-QA based on the following two ideas. First, implicitly expressed causalities in one text might be expressed in other texts with explicit cues. If we can automatically recognize such explicitly expressed causalities from a text archive and use them to complement the implicitly expressed causalities in an answer passage, we can improve why-QA. Second, the causes of similar events tend to be described with a similar set of words (e.g., "seismic energy" and "tectonic plates" for "the Great East Japan Earthquake" and "the 1906 San Francisco Earthquake"). As such, even if we cannot find in a text archive any explicitly expressed cause of an event (e.g., "the Great East Japan Earthquake") expressed in a question (e.g., "Why did the Great East Japan earthquake happen?"), we might be able to identify its implicitly expressed causes with a set of words (e.g., "tectonic plates") that appear in the explicitly expressed cause of a similar event (e.g., "the 1906 San Francisco Earthquake").

This paper proposes a method for intrasentential subject zero anaphora resolution in Japanese.Our proposed method utilizes a Multi-column Convolutional Neural Network (MCNN) for predicting zero anaphoric relations.Motivated by Centering Theory and other previous works, we exploit as clues both the surface word sequence and the dependency tree of a target sentence in our MCNN.Even though the F-score of our method was lower than that of the state-of-the-art method, which achieved relatively high recall and low precision, our method achieved much higher precision (>0.8) in a wide range of recall levels.We believe such high precision is crucial for real-world NLP applications and thus our method is preferable to the state-of-the-art method.

With the proliferation of text data on the World-Wide Web, the development of methods for automatically summarizing these data becomes more important. Here, we propose a practical approach for extracting the most relevant sentences from the original document to form a summary. The idea of our approach is to exploit both the local and global properties of sentences. The local property can be considered as clusters of significant words within each sentence, while the global property can be though of as relations of all sentences in the document. These two properties are combined to get a single measure reflecting the informativeness of sentences. Experimental results show that our approach compares favorably to a commercial text summarizer.

Text classification is the process of classifying documents into predefined categories based on their content. Existing supervised learning algorithms to automatically classify text need sufficient labeled documents to learn accurately. Applying the Expectation-Maximization (EM) algorithm to this problem is an alternative approach that utilizes a large pool of unlabeled documents to augment the available labeled documents. Unfortunately, the time needed to learn with these large unlabeled documents is too high. This paper introduces a novel parallel learning algorithm for text classification task. The parallel algorithm is based on the combination of the EM algorithm and the naive Bayes classifier. Our goal is to improve the computational time in learning and classifying process. We studied the performance of our parallel algorithm on a large Linux PC cluster called PIRUN Cluster. We report both timing and accuracy results. These results indicate that the proposed parallel algorithm is capable of handling large document collections.