Query Resolution for Conversational Search with Limited Supervision

@article{Voskarides2020QueryRF,
  title={Query Resolution for Conversational Search with Limited Supervision},
  author={Nikos Voskarides and Dan Li and Pengjie Ren and E. Kanoulas and M. de Rijke},
  journal={Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval},
  year={2020}
}
  • Nikos VoskaridesDan Li M. de Rijke
  • Published 24 May 2020
  • Computer Science
  • Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval
In this work we focus on multi-turn passage retrieval as a crucial component of conversational search. One of the key challenges in multi-turn passage retrieval comes from the fact that the current turn query is often underspecified due to zero anaphora, topic change, or topic return. Context from the conversational history can be used to arrive at a better expression of the current turn query, defined as the task of query resolution. In this paper, we model the query resolution task as a… 

Zero-shot Query Contextualization for Conversational Search

This work adapts a pre-trained token-level dense retriever on ad-hoc search data to perform conversational search with no additional fine-tuning and performs an analysis that provides insights of how contextualization works in the latent space, in essence introducing a bias towards salient terms from the conversation.

Leveraging Query Resolution and Reading Comprehension for Conversational Passage Retrieval

This paper describes the participation of UvA.ILPS group at the TREC CAsT 2020 track and uses QuReTeC, a binary term classification query resolution model, to address conversational passage retrieval challenges.

Multi-Stage Conversational Passage Retrieval: An Approach to Fusing Term Importance Estimation and Neural Query Rewriting

This article proposes two conversational query reformulation (CQR) methods: (1) term importance estimation and (2) neural query rewriting, which expand conversational queries using important terms extracted from the conversational context with frequency-based signals and reformulation into natural queries with a pretrained sequence-to-sequence model.

Contextualized Query Embeddings for Conversational Search

A compact and effective model for low-latency passage retrieval in Conversational search based on learned dense representations that effectively rewrites conversational queries as dense representations in conversational search and open-domain question answering datasets is described.

McQueen: a Benchmark for Multimodal Conversational Query Rewrite

A large-scale dataset named McQueen, which contains 15k visual conversations and over 80k queries where each one is associated with a fully-specified rewrite version, is collected and used to benchmark a state-of-the-art method for effectively tackling the McQR task, which is based on a multimodal pre-trained model with pointer generator.

Keyword Extraction for Improved Document Retrieval in Conversational Search

This paper collects two conversational keyword extraction datasets and proposes an end-to-end document retrieval pipeline incorporating them, and studies the performance of two neural keyword extraction models, namely, BERT and sequence to sequence, in terms of extraction accuracy and human annotation.

CONQRR: Conversational Query Rewriting for Retrieval with Reinforcement Learning

A query rewriting model C ON QRR is developed that rewrites a conversational question in the context into a standalone question and is trained with a novel reward function to directly optimize towards retrieval using reinforcement learning and can be adapted to any off-the-shelf retriever.

BERT Embeddings Can Track Context in Conversational Search

This work used a Transformer-based re-ranking method and expanded this architecture to use the conversational context and showed the advantages of using the context present in the natural language utterances and in the neural embeddings generated throughout the conversation.

CoSPLADE: Contextualizing SPLADE for Conversational Information Retrieval

By relying on SPLADE sparse representations, it is shown that, when combined with a second-stage ranker based on T5Mono, the results are competitive on the TREC CAsT 2020 and 2021 tracks.

Few-Shot Conversational Dense Retrieval

The analyses reveal that the advantages of ConvDR come from its ability to capture informative context while ignoring the unrelated context in previous conversation rounds, which makes ConvDR more effective as conversations evolve while previous systems may get confused by the increased noise from previous turns.
...

References

SHOWING 1-10 OF 55 REFERENCES

Attentive History Selection for Conversational Question Answering

This work proposes a positional history answer embedding method to encode conversation history with position information using BERT in a natural way, and shows that position information plays an important role in conversation history modeling.

Incomplete Follow-up Question Resolution using Retrieval based Sequence to Sequence Learning

This work presents a retrieval based sequence to sequence learning system that can generate the complete (or intended) question for an incomplete follow-up question (given the conversation context) and demonstrates the utility of the system as a plug-in module to an existing QA pipeline.

Task-Oriented Query Reformulation with Reinforcement Learning

This work introduces a query reformulation system based on a neural network that rewrites a query to maximize the number of relevant documents returned and trains this neural network with reinforcement learning.

QuAC: Question Answering in Context

QuAC introduces challenges not found in existing machine comprehension datasets: its questions are often more open-ended, unanswerable, or only meaningful within the dialog context, as it shows in a detailed qualitative evaluation.

CoQA: A Conversational Question Answering Challenge

CoQA is introduced, a novel dataset for building Conversational Question Answering systems and it is shown that conversational questions have challenging phenomena not present in existing reading comprehension datasets (e.g., coreference and pragmatic reasoning).

Can You Unpack That? Learning to Rewrite Questions-in-Context

This work constructs, CANARD, a dataset of 40,527 questions based on QuAC and trains Seq2Seq models for incorporating context into standalone questions and introduces the task of question-in-context rewriting.

Effective Structured Query Formulation for Session Search

By formulating structured query using the nuggets, this work greatly boost the search accuracy than just using qn, and experiment three weighting schemes, uniform, uniform and distance-based, which find that previous vs. current achieves the best search accuracy.

A statistical approach for Non-Sentential Utterance Resolution for Interactive QA System

This paper adapts the keyword to question (K2Q) framework to generate natural language questions using keywords appearing in an NSU and its context and shows that the proposed method perform significantly better than the previous work that has largely been rule based.

UMass at TREC 2004: Novelty and HARD

The primary findings for passage retrieval are that document retrieval methods performed better than passage retrieval methods on the passage evaluation metric of binary preference at 12,000 characters, and that clarification forms improved passage retrieval for every retrieval method explored.

Distantly Supervised NER with Partial Annotation Learning and Reinforcement Learning

This paper proposes a novel approach which can partially solve the above problems of distant supervision for NER, and applies partial annotation learning to reduce the effect of unknown labels of characters in incomplete and noisy annotations.
...