Related papers: Mining Clues from Incomplete Utterance: A Query-en…
We introduce a new paradigm of learning for reasoning, understanding, and prediction, as well as the scaffolding network to implement this paradigm. The scaffolding network embodies an incremental learning approach that is formulated as a…
Numerical reasoning over hybrid data containing tables and long texts has recently received research attention from the AI community. To generate an executable reasoning program consisting of math and table operations to answer a question,…
The Transformer-Kernel (TK) model has demonstrated strong reranking performance on the TREC Deep Learning benchmark -- and can be considered to be an efficient (but slightly less effective) alternative to other Transformer-based…
Recent Quality Estimation (QE) models based on multilingual pre-trained representations have achieved very competitive results when predicting the overall quality of translated sentences. Predicting translation errors, i.e. detecting…
Although sequence-to-sequence models often achieve good performance in semantic parsing for i.i.d. data, their performance is still inferior in compositional generalization. Several data augmentation methods have been proposed to alleviate…
We introduce a Recursive INsertion-based Encoder (RINE), a novel approach for semantic parsing in task-oriented dialog. Our model consists of an encoder network that incrementally builds the semantic parse tree by predicting the…
We present SummaRuNNer, a Recurrent Neural Network (RNN) based sequence model for extractive summarization of documents and show that it achieves performance better than or comparable to state-of-the-art. Our model has the additional…
Query Expansion (QE) improves retrieval performance by enriching queries with related terms. Recently, Large Language Models (LLMs) have been used for QE, but existing methods face a trade-off: generating diverse terms boosts performance…
A question answering system that in addition to providing an answer provides an explanation of the reasoning that leads to that answer has potential advantages in terms of debuggability, extensibility and trust. To this end, we propose QED,…
Query Auto Completion (QAC), as the starting point of information retrieval tasks, is critical to user experience. Generally it has two steps: generating completed query candidates according to query prefixes, and ranking them based on…
In monolingual dense retrieval, lots of works focus on how to distill knowledge from cross-encoder re-ranker to dual-encoder retriever and these methods achieve better performance due to the effectiveness of cross-encoder re-ranker.…
Query reformulation aims to alter noisy or ambiguous text sequences into coherent ones closer to natural language questions. This is to prevent errors from propagating in a client-facing pipeline and promote better communication with users.…
Text-to-image retrieval is a fundamental task in vision-language learning, yet in real-world scenarios it is often challenged by short and underspecified user queries. Such queries are typically only one or two words long, rendering them…
Query expansion aims to mitigate the mismatch between the language used in a query and in a document. However, query expansion methods can suffer from introducing non-relevant information when expanding the query. To bridge this gap,…
Conversational search aims to retrieve passages containing essential information to answer queries in a multi-turn conversation. In conversational search, reformulating context-dependent conversational queries into stand-alone forms is…
We investigate response selection for multi-turn conversation in retrieval-based chatbots. Existing studies pay more attention to the matching between utterances and responses by calculating the matching score based on learned features,…
Conversational search seeks to retrieve relevant passages for the given questions in conversational question answering. Conversational Query Reformulation (CQR) improves conversational search by refining the original queries into…
Image paragraph captioning aims to describe a given image with a sequence of coherent sentences. Most existing methods model the coherence through the topic transition that dynamically infers a topic vector from preceding sentences.…
We introduce a novel schema for sequence to sequence learning with a Deep Q-Network (DQN), which decodes the output sequence iteratively. The aim here is to enable the decoder to first tackle easier portions of the sequences, and then turn…
Retrieval augmented generation (RAG) pipelines are commonly used in tasks such as question-answering (QA), relying on retrieving relevant documents from a vector store computed using a pretrained embedding model. However, if the retrieved…