Related papers: Learning Autocomplete Systems as a Communication G…
Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. Unfortunately, existing automatic evaluation metrics are biased and correlate very poorly with human judgements of response…
Expanding new functionalities efficiently is an ongoing challenge for single-turn task-oriented dialogue systems. In this work, we explore functionality-specific semi-supervised learning via self-training. We consider methods that augment…
Autoregressive language models, pretrained using large text corpora to do well on next word prediction, have been successful at solving many downstream tasks, even with zero-shot usage. However, there is little theoretical understanding of…
Humans leverage shared conversational context to become increasingly successful and efficient at communicating over time. One manifestation of this is the formation of ad hoc linguistic conventions, which allow people to coordinate on…
In this paper we describe an approach to automatic evaluation of both the speech recognition and understanding capabilities of a spoken dialogue system for train time table information. We use word accuracy for recognition and concept…
We propose a novel framework to learn how to communicate with intent, i.e., to transmit messages over a wireless communication channel based on the end-goal of the communication. This stays in stark contrast to classical communication…
The eventual goal of a language model is to accurately predict the value of a missing word given its context. We present an approach to word prediction that is based on learning a representation for each word as a function of words and…
Task-oriented dialogue (TOD) systems facilitate users in executing various activities via multi-turn dialogues, but Large Language Models (LLMs) often struggle to comprehend these intricate contexts. In this study, we propose a novel…
Word-Level Auto-Completion (WLAC) plays a crucial role in Computer-Assisted Translation. It aims at providing word-level auto-completion suggestions for human translators. While previous studies have primarily focused on designing complex…
Text semantic matching is a fundamental task that has been widely used in various scenarios, such as community question answering, information retrieval, and recommendation. Most state-of-the-art matching models, e.g., BERT, directly…
Large language models (LLMs) process entire input contexts indiscriminately, which is inefficient when the information required to answer a query is localized within the context. We present dynamic context cutoff, a novel method enabling…
A key functionality of emerging connected autonomous systems such as smart cities, smart transportation systems, and the industrial Internet-of-Things, is the ability to process and learn from data collected at different physical locations.…
The majority of research in computational psycholinguistics has concentrated on the processing of words. This study introduces innovative methods for computing sentence-level metrics using multilingual large language models. The metrics…
We consider the issue of multiple agents learning to communicate through reinforcement learning within partially observable environments, with a focus on information asymmetry in the second part of our work. We provide a review of the…
Achieving more powerful semantic representations and semantic understanding is one of the key problems in improving the performance of semantic communication systems. This work focuses on enhancing the semantic understanding of the text…
Simultaneous translation, which starts translating each sentence after receiving only a few words in source sentence, has a vital role in many scenarios. Although the previous prefix-to-prefix framework is considered suitable for…
Designing a spoken language understanding system for command-and-control applications can be challenging because of a wide variety of domains and users or because of a lack of training data. In this paper we discuss a system that learns…
An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its coverage of experience/data is broad enough,…
Code completion is a popular software development tool integrated into all major IDEs. Many neural language models have achieved promising results in completion suggestion prediction on synthetic benchmarks. However, a recent study When…
Designing machine intelligence to converse with a human user necessarily requires an understanding of how humans participate in conversation, and thus conversation modeling is an important task in natural language processing. New…