Related papers: Enhance Incomplete Utterance Restoration by Joint …

When a multi-agent system produces an incorrect or harmful answer, who is accountable if execution logs and agent identifiers are unavailable? In practice, generated content is often detached from its execution environment due to privacy or…

Unpaired data has shown to be beneficial for low-resource automatic speech recognition~(ASR), which can be involved in the design of hybrid models with multi-task training or language model dependent pre-training. In this work, we leverage…

Rule extraction is a central problem in interpretable machine learning because it seeks to convert opaque predictive behavior into human-readable symbolic structure. This paper presents Chat Incremental Pattern Constructor (ChatIPC), a…

The Incomplete Utterance Rewriting (IUR) task has garnered significant attention in recent years. Its goal is to reconstruct conversational utterances to better align with the current context, thereby enhancing comprehension. In this paper,…

Error recovery is an essential feature for a parser that should be plugged in Integrated Development Environments (IDEs), which must build Abstract Syntax Trees (ASTs) even for syntactically invalid programs in order to offer features such…

Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a collection of supporting documents. One of the most…

Transformers have demonstrated strong potential in offline reinforcement learning (RL) by modeling trajectories as sequences of return-to-go, states, and actions. However, existing approaches such as the Decision Transformer(DT) and its…

Existing Incremental Object Detection (IOD) methods partially alleviate catastrophic forgetting when incrementally detecting new objects in real-world scenarios. However, many of these methods rely on the assumption that unlabeled old-class…

Knowledge-intensive language tasks (KILTs) benefit from retrieving high-quality relevant contexts from large external knowledge corpora. Learning task-specific retrievers that return relevant contexts at an appropriate level of semantic…

The results of information retrieval (IR) are usually presented in the form of a ranked list of candidate documents, such as web search for humans and retrieval-augmented generation for large language models (LLMs). List-aware retrieval…

We introduce EXIT, an extractive context compression framework that enhances both the effectiveness and efficiency of retrieval-augmented generation (RAG) in question answering (QA). Current RAG systems often struggle when retrieval models…

Multimodal emotion recognition utilizes complete multimodal information and robust multimodal joint representation to gain high performance. However, the ideal condition of full modality integrity is often not applicable in reality and…

Dialogue systems in open domain have achieved great success due to the easily obtained single-turn corpus and the development of deep learning, but the multi-turn scenario is still a challenge because of the frequent coreference and…

Pre-trained transformer models shine in many natural language processing tasks and therefore are expected to bear the representation of the input sentence or text meaning. These sentence-level embeddings are also important in…

Textbook question answering (TQA) is a complex task, requiring the interpretation of complex multimodal context. Although recent advances have improved overall performance, they often encounter difficulties in educational settings where…

Despite the significant progress of fully-supervised video captioning, zero-shot methods remain much less explored. In this paper, we propose a novel zero-shot video captioning framework named Retrieval-Enhanced Test-Time Adaptation…

Unsupervised learning of low-dimensional, semantic representations of words and entities has recently gained attention. In this paper we describe the Semantic Entity Retrieval Toolkit (SERT) that provides implementations of our previously…

We introduce SetBERT, a fine-tuned BERT-based model designed to enhance query embeddings for set operations and Boolean logic queries, such as Intersection (AND), Difference (NOT), and Union (OR). SetBERT significantly improves retrieval…

Language models trained on web-scale corpora risk memorizing and exposing sensitive information, prompting the need for effective machine unlearning. Prior methods mainly focus on input queries to suppress sensitive outputs, yet this often…

Active learning has been shown to be an effective way to alleviate some of the effort required in utilising large collections of unlabelled data for machine learning tasks without needing to fully label them. The representation mechanism…