Published on Tue Oct 08 2019

Look before you Hop: Conversational Question Answering over Knowledge Graphs Using Judicious Context Expansion

Philipp Christmann, Rishiraj Saha Roy, Abdalghani Abujabal, Jyotsna Singh, Gerhard Weikum

Conversational questions are often incomplete, with entities or predicates left out. This poses a huge challenge to question answering (QA) systems that rely on cues in full-fledged interrogative sentences. We develop CONVEX: an unsupervised method that can answercomplete questions.

0
0
0
Abstract

Fact-centric information needs are rarely one-shot; users typically ask follow-up questions to explore a topic. In such a conversational setting, the user's inputs are often incomplete, with entities or predicates left out, and ungrammatical phrases. This poses a huge challenge to question answering (QA) systems that typically rely on cues in full-fledged interrogative sentences. As a solution, we develop CONVEX: an unsupervised method that can answer incomplete questions over a knowledge graph (KG) by maintaining conversation context using entities and predicates seen so far and automatically inferring missing or ambiguous pieces for follow-up questions. The core of our method is a graph exploration algorithm that judiciously expands a frontier to find candidate answers for the current question. To evaluate CONVEX, we release ConvQuestions, a crowdsourced benchmark with 11,200 distinct conversations from five different domains. We show that CONVEX: (i) adds conversational support to any stand-alone QA system, and (ii) outperforms state-of-the-art baselines and question completion strategies.

Tue May 11 2021
NLP
Reinforcement Learning from Reformulations in Conversational Question Answering over Knowledge Graphs
Conversational question answering (ConvQA) is a popular mechanism for user-system interaction. State-of-the-art methods for ConvQA over knowledge graphs (KGs) can only learn from crisp question-answer pairs. We present a reinforcement learning model, termed CONQUER,
2
1
2
Wed Sep 01 2021
NLP
Structured Context and High-Coverage Grammar for Conversational Question Answering over Knowledge Graphs
We tackle the problem of weakly-supervised conversational Question Answering using a neural semantic parsing approach. We create a new Logical Form (LF) grammar that can model a wide range of queries on the graph while remaining sufficiently simple to generate supervision data efficiently.
0
0
0
Wed Jan 31 2018
NLP
Complex Sequential Question Answering: Towards Learning to Converse Over Linked Question Answer Pairs with a Knowledge Graph
Complex Sequential QA combines the two tasks of answering factual questions through complex inferencing over a realistic-sized KG of millions of entities. Through a labor intensive process, involving in-house and crowdsourced workers, we created around 200K dialogs with a total of 1.6M turns.
0
0
0
Fri May 22 2020
NLP
Open-Retrieval Conversational Question Answering
Conversational search is one of the ultimate goals of information retrieval. We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers.
0
0
0
Tue Apr 13 2021
NLP
QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering
The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges. Here we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: relevance scoring and joint reasoning.
4
66
260
Fri May 14 2021
NLP
QAConv: Question Answering on Informative Conversations
QAConv is a new question answering (QA) dataset that uses conversations as a knowledge source. The conversations are usually long, complex, and involve strong domain knowledge. The dataset has two testing scenarios, chunk mode and full mode.
3
9
79