As machine translation increasingly requires deeper contextual, linguistic, and cultural understanding, multi-agent collaboration has emerged as a promising approach. Multi-agent debate (MAD) frameworks, in which multiple agents deliberate to produce a final output, have shown strong performance on objective tasks, but remain underexplored in translation, where multiple valid renderings often exist. We adapt three MAD frameworks for English-Japanese translation and evaluate them against strong generative baselines, reasoning-capable LLMs, and a prompt-based self-reflection baseline. Across general-domain and culturally grounded datasets, the Society of Mind (SoM) variant yields the strongest results in the English-to-Japanese direction, showing that zero-shot translations leave substantial room for improvement through structured deliberation. Yet the gains of debate are front-loaded: later rounds do not reliably improve quality and often reintroduce translation errors. Diagnostic and error-span analyses show that hand-designed debate protocols tend to over-revise already strong translations, leading to semantic drift and process-induced degradation. These findings highlight both the promise and the limitations of agentic translation, and suggest that effective debate-based systems require mechanisms for preserving strong intermediate outputs.

The task of quote attribution seeks to pair textual utterances with the name of their speakers. Despite continuing research efforts on the task, models are rarely evaluated systematically against previous models in comparable settings on the same datasets. This has resulted in a poor understanding of the relative strengths and weaknesses of various approaches. In this work we formalize the task of quote attribution, and in doing so, establish a basis of comparison across existing models. We present an exhaustive benchmark of known models, including natural extensions to larger LLM base models, on all available datasets in both English and Chinese. Our benchmarking results reveal that the CEQA model attains state-of-the-art performance among all supervised methods, and ChatGPT, operating in a four-shot setting, demonstrates performance on par with or surpassing that of supervised methods on some datasets. Detailed error analysis identify several key factors contributing to prediction errors.

When engaging in conversations, dialogue agents in a virtual simulation environment may exhibit their own emotional states that are unrelated to the immediate conversational context, a phenomenon known as self-emotion.This study explores how such self-emotion affects the agents' behaviors in dialogue strategies and decision-making within a large language model (LLM)-driven simulation framework.In a dialogue strategy prediction experiment, we analyze the dialogue strategy choices employed by agents both with and without self-emotion, comparing them to those of humans.The results show that incorporating self-emotion helps agents exhibit more human-like dialogue strategies.In an independent experiment comparing the performance of models fine-tuned on GPT-4 generated dialogue datasets, we demonstrate that self-emotion can lead to better overall naturalness and humanness.Finally, in a virtual simulation environment where agents have discussions on multiple topics, we show that self-emotion of agents can significantly influence the decision-making process of the agents, leading to approximately a 50% change in decisions.

We explore the idea of incorporating concepts from writing skills curricula into humanmachine collaborative writing scenarios, focusing on adding writing modes as a control for text generation models.Using crowd-sourced workers, we annotate a corpus of narrative text paragraphs with writing mode labels.Classifiers trained on this data achieve an average accuracy of ∼ 87% on held-out data.We finetune a set of large language models to condition on writing mode labels, and show that the generated text is recognized as belonging to the specified mode with high accuracy.To study the ability of writing modes to provide fine-grained control over generated text, we devise a novel turn-based text reconstruction game to evaluate the difference between the generated text and the author's intention.We show that authors prefer text suggestions made by writing mode-controlled models on average 61.1% of the time, with satisfaction scores 0.5 higher on a 5-point ordinal scale.When evaluated by humans, stories generated via collaboration with writing mode-controlled models achieve high similarity with the professionally written target story.We conclude by identifying the most common mistakes found in the generated stories.The datasets and codes are available at the Github 1 .

We release Amp-Space, a large-scale dataset of paired audio samples: a source audio signal, and an output signal, the result of a timbre transformation. The types of transformations we study are from blackbox musical tools (amplifiers, stompboxes, studio effects) traditionally used to shape the sound of guitar, bass, or synthesizer sounds. For each sample of transformed audio, the set of parameters used to create it are given. Samples are from both real and simulated devices, the latter allowing for orders of magnitude greater data than found in comparable datasets. We demonstrate potential use cases of this data by (a) pre-training a conditional WaveNet model on synthetic data and show that it reduces the number of samples necessary to digitally reproduce a real musical device, and (b) training a variational autoencoder to shape a continuous space of timbre transformations for creating new sounds through interpolation.

We propose a hierarchical meta-learning-inspired model for music source separation (Meta-TasNet) in which a generator model is used to predict the weights of individual extractor models. This enables efficient parameter-sharing, while still allowing for instrument-specific parameterization. Meta-TasNet is shown to be more effective than the models trained independently or in a multi-task setting, and achieve performance comparable with state-of-the-art methods. In comparison to the latter, our extractors contain fewer parameters and have faster run-time performance. We discuss important architectural considerations, and explore the costs and benefits of this approach.

Statistical morphological inflectors are typically trained on fully supervised, type-level data.One remaining open research question is the following: How can we effectively exploit raw, token-level data to improve their performance?To this end, we introduce a novel generative latent-variable model for the semi-supervised learning of inflection generation.To enable posterior inference over the latent variables, we derive an efficient variational inference procedure based on the wake-sleep algorithm.We experiment on 23 languages, using the Universal Dependencies corpora in a simulated low-resource setting, and find improvements of over 10% absolute accuracy in some cases.

Neural architectures are prominent in the construction of language models (LMs). However, word-level prediction is typically agnostic of subword-level information (characters and character sequences) and operates over a closed vocabulary, consisting of a limited word set. Indeed, while subword-aware models boost performance across a variety of NLP tasks, previous work did not evaluate the ability of these models to assist next-word prediction in language modeling tasks. Such subword-level informed models should be particularly effective for morphologically-rich languages (MRLs) that exhibit high type-to-token ratios. In this work, we present a large-scale LM study on 50 typologically diverse languages covering a wide variety of morphological systems, and offer new LM benchmarks to the community, while considering subword-level information. The main technical contribution of our work is a novel method for injecting subword-level information into semantic word vectors, integrated into the neural language modeling training, to facilitate word-level prediction. We conduct experiments in the LM setting where the number of infrequent words is large, and demonstrate strong perplexity gains across our 50 languages, especially for morphologically-rich languages. Our code and data sets are publicly available.

Comprehending lyrics, as found in songs and poems, can pose a challenge to human and machine readers alike. This motivates the need for systems that can understand the ambiguity and jargon found in such creative texts, and provide commentary to aid readers in reaching the correct interpretation. We introduce the task of automated lyric annotation (ALA). Like text simplification, a goal of ALA is to rephrase the original text in a more easily understandable manner. However, in ALA the system must often include additional information to clarify niche terminology and abstract concepts. To stimulate research on this task, we release a large collection of crowdsourced annotations for song lyrics. We analyze the performance of translation and retrieval models on this task, measuring performance with both automated and human evaluation. We find that each model captures a unique type of information important to the task.

Given that in practice training data is scarce for all but a small set of problems, a core question is how to incorporate prior knowledge into a model. In this paper, we consider the case of prior procedural knowledge for neural networks, such as knowing how a program should traverse a sequence, but not what local actions should be performed at each step. To this end, we present an end-to-end differentiable interpreter for the programming language Forth which enables programmers to write program sketches with slots that can be filled with behaviour trained from program input-output data. We can optimise this behaviour directly through gradient descent techniques on user-specified objectives, and also integrate the program into any larger neural computation graph. We show empirically that our interpreter is able to effectively leverage different levels of prior program structure and learn complex behaviours such as sequence sorting and addition. When connected to outputs of an LSTM and trained jointly, our interpreter achieves state-of-the-art accuracy for end-to-end reasoning about quantities expressed in natural language stories.

Semantic parsers map natural language statements into meaning representations, and must abstract over syntactic phenomena, resolve anaphora, and identify word senses to eliminate ambiguous interpretations.Abstract meaning representation (AMR) is a recent example of one such semantic formalism which, similar to a dependency parse, utilizes a graph to represent relationships between concepts (Banarescu et al., 2013).As with dependency parsing, transition-based approaches are a common approach to this problem.However, when trained in the traditional manner these systems are susceptible to the accumulation of errors when they find undesirable states during greedy decoding.Imitation learning algorithms have been shown to help these systems recover from such errors.To effectively use these methods for AMR parsing we find it highly beneficial to introduce two novel extensions: noise reduction and targeted exploration.The former mitigates the noise in the feature representation, a result of the complexity of the task.The latter targets the exploration steps of imitation learning towards areas which are likely to provide the most information in the context of a large action-space.We achieve state-ofthe art results, and improve upon standard transition-based parsing by 4.7 F 1 points.

Sameer Singh, Tim Rocktäschel, Luke Hewitt, Jason Naradowsky, Sebastian Riedel. Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Demonstrations. 2015.