Rishiraj Saha Roy

Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum

Conversational question answering (ConvQA) tackles sequential information needs where contexts in follow-up questions are left implicit. Current ConvQA systems operate over homogeneous sources of information: either a knowledge base (KB), or a text corpus, or a collection of tables. This paper addresses the novel issue of jointly tapping into all of these together, this way boosting answer coverage and confidence. We present CONVINSE, an end-to-end pipeline for ConvQA over heterogeneous sources, operating in three stages: i) learning an explicit structured representation of an incoming question and its conversational context, ii) harnessing this frame-like representation to uniformly capture relevant evidences from KB, text, and tables, and iii) running a fusion-in-decoder model to generate the answer. We construct and release the first benchmark, ConvMix, for ConvQA over heterogeneous sources, comprising 3000 real-user conversations with 16000 questions, along with entity annotations, completed question utterances, and question paraphrases. Experiments demonstrate the viability and advantages of our method, compared to state-of-the-art baselines.

Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum

Models for conversational question answering (ConvQA) over knowledge graphs (KGs) are usually trained and tested on benchmarks of gold QA pairs. This implies that training is limited to surface forms seen in the respective datasets, and evaluation is on a small set of held-out questions. Through our proposed framework REIGN, we take several steps to remedy this restricted learning setup. First, we systematically generate reformulations of training questions to increase robustness of models to surface form variations. This is a particularly challenging problem, given the incomplete nature of such questions. Second, we guide ConvQA models towards higher performance by feeding it only those reformulations that help improve their answering quality, using deep reinforcement learning. Third, we demonstrate the viability of training major model components on one benchmark and applying them zero-shot to another. Finally, for a rigorous evaluation of robustness for trained models, we use and release large numbers of diverse reformulations generated by prompting GPT for benchmark test sets (resulting in 20x increase in sizes). Our findings show that ConvQA models with robust training via reformulations, significantly outperform those with standard training from gold QA pairs only.

Rishiraj Saha Roy, Joel Schlotthauer, Chris Hinze et al.

Retrieval Augmented Generation (RAG) works as a backbone for interacting with an enterprise's own data via Conversational Question Answering (ConvQA). In a RAG system, a retriever fetches passages from a collection in response to a question, which are then included in the prompt of a large language model (LLM) for generating a natural language (NL) answer. However, several RAG systems today suffer from two shortcomings: (i) retrieved passages usually contain their raw text and lack appropriate document context, negatively impacting both retrieval and answering quality; and (ii) attribution strategies that explain answer generation typically rely only on similarity between the answer and the retrieved passages, thereby only generating plausible but not causal explanations. In this work, we demonstrate RAGONITE, a RAG system that remedies the above concerns by: (i) contextualizing evidence with source metadata and surrounding text; and (ii) computing counterfactual attribution, a causal explanation approach where the contribution of an evidence to an answer is determined by the similarity of the original response to the answer obtained by removing that evidence. To evaluate our proposals, we release a new benchmark ConfQuestions: it has 300 hand-created conversational questions, each in English and German, coupled with ground truth URLs, completed questions, and answers from 215 public Confluence pages. These documents are typical of enterprise wiki spaces with heterogeneous elements. Experiments with RAGONITE on ConfQuestions show the viability of our ideas: contextualization improves RAG performance, and counterfactual explanations outperform standard attribution.

Rishiraj Saha Roy, Chris Hinze, Joel Schlotthauer et al.

Conversational question answering (ConvQA) is a convenient means of searching over RDF knowledge graphs (KGs), where a prevalent approach is to translate natural language questions to SPARQL queries. However, SPARQL has certain shortcomings: (i) it is brittle for complex intents and conversational questions, and (ii) it is not suitable for more abstract needs. Instead, we propose a novel two-pronged system where we fuse: (i) SQL-query results over a database automatically derived from the KG, and (ii) text-search results over verbalizations of KG facts. Our pipeline supports iterative retrieval: when the results of any branch are found to be unsatisfactory, the system can automatically opt for further rounds. We put everything together in a retrieval augmented generation (RAG) setup, where an LLM generates a coherent response from accumulated search results. We demonstrate the superiority of our proposed system over several baselines on a knowledge graph of BMW automobiles.

Soumajit Pramanik, Jesujoba Alabi, Rishiraj Saha Roy et al.

Question answering over RDF data like knowledge graphs has been greatly advanced, with a number of good systems providing crisp answers for natural language questions or telegraphic queries. Some of these systems incorporate textual sources as additional evidence for the answering process, but cannot compute answers that are present in text alone. Conversely, the IR and NLP communities have addressed QA over text, but such systems barely utilize semantic data and knowledge. This paper presents a method for complex questions that can seamlessly operate over a mixture of RDF datasets and text corpora, or individual sources, in a unified framework. Our method, called UNIQORN, builds a context graph on-the-fly, by retrieving question-relevant evidences from the RDF data and/or a text corpus, using fine-tuned BERT models. The resulting graph typically contains all question-relevant evidences but also a lot of noise. UNIQORN copes with this input by a graph algorithm for Group Steiner Trees, that identifies the best answer candidates in the context graph. Experimental results on several benchmarks of complex questions with multiple entities and relations, show that UNIQORN significantly outperforms state-of-the-art methods for heterogeneous QA - in a full training mode, as well as in zero-shot settings. The graph-based methodology provides user-interpretable evidence for the complete answering process.

Philipp Christmann, Rishiraj Saha Roy, Gerhard Weikum

Answering complex questions over knowledge bases (KB-QA) faces huge input data with billions of facts, involving millions of entities and thousands of predicates. For efficiency, QA systems first reduce the answer search space by identifying a set of facts that is likely to contain all answers and relevant cues. The most common technique for doing this is to apply named entity disambiguation (NED) systems to the question, and retrieve KB facts for the disambiguated entities. This work presents CLOCQ, an efficient method that prunes irrelevant parts of the search space using KB-aware signals. CLOCQ uses a top-k query processor over score-ordered lists of KB items that combine signals about lexical matching, relevance to the question, coherence among candidate items, and connectivity in the KB graph. Experiments with two recent QA benchmarks for complex questions demonstrate the superiority of CLOCQ over state-of-the-art baselines with respect to answer presence, size of the search space, and runtimes.

Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum

The rise of personal assistants has made conversational question answering (ConvQA) a very 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 found in popular benchmarks. In reality, however, such training data is hard to come by: users would rarely mark answers explicitly as correct or wrong. In this work, we take a step towards a more natural learning paradigm - from noisy and implicit feedback via question reformulations. A reformulation is likely to be triggered by an incorrect system response, whereas a new follow-up question could be a positive signal on the previous turn's answer. We present a reinforcement learning model, termed CONQUER, that can learn from a conversational stream of questions and reformulations. CONQUER models the answering process as multiple agents walking in parallel on the KG, where the walks are determined by actions sampled using a policy network. This policy network takes the question along with the conversational context as inputs and is trained via noisy rewards obtained from the reformulation likelihood. To evaluate CONQUER, we create and release ConvRef, a benchmark with about 11k natural conversations containing around 205k reformulations. Experiments show that CONQUER successfully learns to answer conversational questions from noisy reward signals, significantly improving over a state-of-the-art baseline.

Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum

Question answering (QA) over text passages is a problem of long-standing interest in information retrieval. Recently, the conversational setting has attracted attention, where a user asks a sequence of questions to satisfy her information needs around a topic. While this setup is a natural one and similar to humans conversing with each other, it introduces two key research challenges: understanding the context left implicit by the user in follow-up questions, and dealing with ad hoc question formulations. In this work, we demonstrate CROWN (Conversational passage ranking by Reasoning Over Word Networks): an unsupervised yet effective system for conversational QA with passage responses, that supports several modes of context propagation over multiple turns. To this end, CROWN first builds a word proximity network (WPN) from large corpora to store statistically significant term co-occurrences. At answering time, passages are ranked by a combination of their similarity to the question, and coherence of query terms within: these factors are measured by reading off node and edge weights from the WPN. CROWN provides an interface that is both intuitive for end-users, and insightful for experts for reconfiguration to individual setups. CROWN was evaluated on TREC CAsT data, where it achieved above-median performance in a pool of neural methods.

Magdalena Kaiser, Rishiraj Saha Roy, Gerhard Weikum

Information needs around a topic cannot be satisfied in a single turn; users typically ask follow-up questions referring to the same theme and a system must be capable of understanding the conversational context of a request to retrieve correct answers. In this paper, we present our submission to the TREC Conversational Assistance Track 2019, in which such a conversational setting is explored. We propose a simple unsupervised method for conversational passage ranking by formulating the passage score for a query as a combination of similarity and coherence. To be specific, passages are preferred that contain words semantically similar to the words used in the question, and where such words appear close by. We built a word-proximity network (WPN) from a large corpus, where words are nodes and there is an edge between two nodes if they co-occur in the same passages in a statistically significant way, within a context window. Our approach, named CROWN, improved nDCG scores over a provided Indri baseline on the CAsT training data. On the evaluation data for CAsT, our best run submission achieved above-average performance with respect to AP@5 and nDCG@1000.

Zhen Jia, Abdalghani Abujabal, Rishiraj Saha Roy et al.

Question answering over knowledge bases (KB-QA) poses challenges in handling complex questions that need to be decomposed into sub-questions. An important case, addressed here, is that of temporal questions, where cues for temporal relations need to be discovered and handled. We present TEQUILA, an enabler method for temporal QA that can run on top of any KB-QA engine. TEQUILA has four stages. It detects if a question has temporal intent. It decomposes and rewrites the question into non-temporal sub-questions and temporal constraints. Answers to sub-questions are then retrieved from the underlying KB-QA engine. Finally, TEQUILA uses constraint reasoning on temporal intervals to compute final answers to the full question. Comparisons against state-of-the-art baselines show the viability of our method.

Abdalghani Abujabal, Rishiraj Saha Roy, Mohamed Yahya et al.

To bridge the gap between the capabilities of the state-of-the-art in factoid question answering (QA) and what users ask, we need large datasets of real user questions that capture the various question phenomena users are interested in, and the diverse ways in which these questions are formulated. We introduce ComQA, a large dataset of real user questions that exhibit different challenging aspects such as compositionality, temporal reasoning, and comparisons. ComQA questions come from the WikiAnswers community QA platform, which typically contains questions that are not satisfactorily answerable by existing search engine technology. Through a large crowdsourcing effort, we clean the question dataset, group questions into paraphrase clusters, and annotate clusters with their answers. ComQA contains 11,214 questions grouped into 4,834 paraphrase clusters. We detail the process of constructing ComQA, including the measures taken to ensure its high quality while making effective use of crowdsourcing. We also present an extensive analysis of the dataset and the results achieved by state-of-the-art systems on ComQA, demonstrating that our dataset can be a driver of future research on QA.