Related papers: RST Parsing from Scratch
Large language models (LLMs) achieve strong performance by generating long chains of thought, but longer traces always introduce redundant or ineffective reasoning steps. One typical behavior is that they often perform unnecessary…
End-to-end speech-to-speech translation (S2ST) systems typically struggle with a critical data bottleneck: the scarcity of parallel speech-to-speech corpora. To overcome this, we introduce RosettaSpeech, a novel zero-shot framework trained…
Relation extraction typically aims to extract semantic relationships between entities from the unstructured text. One of the most essential data sources for relation extraction is the spoken language, such as interviews and dialogues.…
This paper is concerned with dialogue state tracking (DST) in a task-oriented dialogue system. Building a DST module that is highly effective is still a challenging issue, although significant progresses have been made recently. This paper…
Recent advances in Large Language Models (LLMs) have significantly improved complex reasoning capabilities. Retrieval-Augmented Generation (RAG) has further extended these capabilities by grounding generation in dynamically retrieved…
Headline generation aims to summarize a long document with a short, catchy title that reflects the main idea. This requires accurately capturing the core document semantics, which is challenging due to the lengthy and background…
Measuring sentence similarity is a classic topic in natural language processing. Light-weighted similarities are still of particular practical significance even when deep learning models have succeeded in many other tasks. Some…
Spoken Language Understanding (SLU) is the problem of extracting the meaning from speech utterances. It is typically addressed as a two-step problem, where an Automatic Speech Recognition (ASR) model is employed to convert speech into text,…
We initiate a study of a query-driven approach to designing partition trees for range-searching problems. Our model assumes that a data structure is to be built for an unknown query distribution that we can access through a sampling oracle,…
End-to-end spoken language understanding (SLU) predicts intent directly from audio using a single model. It promises to improve the performance of assistant systems by leveraging acoustic information lost in the intermediate textual…
We propose a new outline for adaptive dictionary learning methods for sparse encoding based on a hierarchical clustering of the training data. Through recursive application of a clustering method, the data is organized into a binary…
Structured texts refer to texts containing structured elements beyond plain texts, such as code snippets and placeholders. Such structured texts increasingly require segmentation into semantically meaningful components, which cannot be…
Automatic evaluation of ST systems is typically performed by comparing translation hypotheses with one or more reference translations. While effective to some extent, this approach inherits the limitation of reference-based evaluation that…
Language exhibits inherent structures, a property that explains both language acquisition and language change. Given this characteristic, we expect language models to manifest their own internal structures as well. While interpretability…
Traversals are commonly seen in tree data structures, and performance-enhancing transformations between tree traversals are critical for many applications. Existing approaches to reasoning about tree traversals and their transformations are…
Generating intermediate steps, or Chain of Thought (CoT), is an effective way to significantly improve language models' (LM) multi-step reasoning capability. However, the CoT lengths can grow rapidly with the problem complexity, easily…
Neural networks with tree-based sentence encoders have shown better results on many downstream tasks. Most of existing tree-based encoders adopt syntactic parsing trees as the explicit structure prior. To study the effectiveness of…
End-to-end (E2E) speech-to-text translation (ST) often depends on pretraining its encoder and/or decoder using source transcripts via speech recognition or text translation tasks, without which translation performance drops substantially.…
We focus on Text-to-SQL semantic parsing from the perspective of retrieval-augmented generation. Motivated by challenges related to the size of commercial database schemata and the deployability of business intelligence solutions, we…
Document-level relation extraction (DocRE) models generally use graph networks to implicitly model the reasoning skill (i.e., pattern recognition, logical reasoning, coreference reasoning, etc.) related to the relation between one entity…