Search for: All records

Conversational search is one of the ultimate goals of information retrieval. Recent research approaches conversational search by simplified settings of response ranking and conversational question answering, where an answer is either selected from a given candidate set or extracted from a given passage. These simplifications neglect the fundamental role of retrieval in conversational search. To address this limitation, we introduce an open-retrieval conversational question answering (ORConvQA) setting, where we learn to retrieve evidence from a large collection before extracting answers, as a further step towards building functional conversational search systems. We create a dataset, OR-QuAC, to facilitate research on ORConvQA. We build an end-to-end system for ORConvQA, featuring a retriever, a reranker, and a reader that are all based on Transformers. Our extensive experiments on OR-QuAC demonstrate that a learnable retriever is crucial for ORConvQA. We further show that our system can make a substantial improvement when we enable history modeling in all system components. Moreover, we show that the reranker component contributes to the model performance by providing a regularization effect. Finally, further in-depth analyses are performed to provide new insights into ORConvQA. 

Conversational AI is a rapidly developing research field in both industry and academia. As one of the major branches of conversational AI, question answering and conversational search has attracted significant attention of researchers in the information retrieval community. It has been a long overdue feature for search engines or conversational assistants to retrieve information iteratively and interactively in a conversational manner. Previous work argues that conversational question answering (ConvQA) is a simplified but concrete setting of conversational search. In this setting, one of the major challenges is to leverage the conversation history to understand and answer the current question. In this work, we propose a novel solution for ConvQA that involves three aspects. First, we propose a positional history answer embedding method to encode conversation history with position information using BERT (Bidirectional Encoder Representations from Transformers) in a natural way. BERT is a powerful technique for text representation. Second, we design a history attention mechanism (HAM) to conduct a "soft selection" for conversation histories. This method attends to history turns with different weights based on how helpful they are on answering the current question. Third, in addition to handling conversation history, we take advantage of multi-task learning (MTL) to do answer prediction along with another essential conversation task (dialog act prediction) using a uniform model architecture. MTL is able to learn more expressive and generic representations to improve the performance of ConvQA. We demonstrate the effectiveness of our model with extensive experimental evaluations on QuAC, a large-scale ConvQA dataset. We show that position information plays an important role in conversation history modeling. We also visualize the history attention and provide new insights into conversation history understanding. The complete implementation of our model will be open-sourced. 

Conversational search is an emerging topic in the information retrieval community. One of the major challenges to multi-turn conversational search is to model the conversation history to understand the current question. Existing methods either prepend history turns to the current question or use complicated attention mechanisms to model the history. We propose a conceptually simple yet highly effective approach referred to as history answer embedding. It enables seamless integration of conversation history into a conversational question answering (ConvQA) model built on BERT (Bidirectional Encoder Representations from Transformers). We first explain our view that ConvQA is a simplified but concrete setting of conversational search, and then we provide a general framework to solve ConvQA. We further demonstrate the effectiveness of our approach under this framework. Finally, we analyze the impact of different numbers of history turns under different settings. We show that history prepending methods degrade dramatically when given a long conversation history while our method is robust and shows advantages under such a situation, which provides new insights into conversation history modeling in ConvQA. 

Intelligent personal assistant systems, with either text-based or voice-based conversational interfaces, are becoming increasingly popular. Most previous research has used either retrieval-based or generation-based methods. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. The retrieved responses are easier to control and explain. However, the response retrieval performance is limited by the size of the response repository. On the other hand, although generation-based methods can return highly coherent responses given conversation context, they are likely to return universal or general responses with insufficient ground knowledge information. In this paper, we build a hybrid neural conversation model with the capability of both response retrieval and generation, in order to combine the merits of these two types of methods. Experimental results on Twitter and Foursquare data show that the proposed model can outperform both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model) under both automatic evaluation metrics and human evaluation. Our models and research findings provide new insights on how to integrate text retrieval and text generation models for building conversation systems. 

Information retrieval systems are evolving from document retrieval to answer retrieval. Web search logs provide large amounts of data about how people interact with ranked lists of documents, but very little is known about interaction with answer texts. In this paper, we use Amazon Mechanical Turk to investigate three answer presentation and interaction approaches in a non-factoid question answering setting. We find that people perceive and react to good and bad answers very differently, and can identify good answers relatively quickly. Our results provide the basis for further investigation of effective answer interaction and feedback methods. 

Understanding and characterizing how people interact in information-seeking conversations will be a crucial component in developing effective conversational search systems. In this paper, we introduce a new dataset designed for this purpose and use it to analyze information-seeking conversations by user intent distribution, co-occurrence, and flow patterns. The MSDialog dataset is a labeled conversation dataset of question answering (QA) interactions between information seekers and providers from an online forum on Microsoft products. The dataset contains more than 2,000 multi-turn QA dialogs with 10,000 utterances that are annotated with user intents on the utterance level. Annotations were done using crowdsourcing. With MSDialog, we find some highly recurring patterns in user intent during an information-seeking process. They could be useful for designing conversational search systems. We will make our dataset freely available to encourage exploration of information-seeking conversation models. 

The effects of annealing time and molecular weight on the strong melt memory effect observed in random ethylene 1‐alkene copolymers are analyzed in a series of model ethylene 1‐butene copolymers with 2.2 mol% branches. Melt memory is associated with molten clusters of ethylene sequences from the initial crystals that remain in close proximity and are unable to diffuse quickly to the randomized melt state, thus increasing the recrystallization rate. Melt memory persists even for greater than 1000 min annealing indicating a long‐lived nature of the clusters that only fully dissolve at melt temperatures above a critical value (>160 °C). Below the critical melt temperature, molecular weight and annealing temperature have a strong influence on the slow kinetics of melt memory. For the copolymers analyzed, slow dissolution of clusters is experimentally observed only forM_w < 50 000 g mol⁻¹. More stable clusters that survive higher annealing temperatures display slower dissolution rates than clusters remaining at lower temperatures. The threshold crystallinity level to enable melt memory (X_c,threshold) decreases with increasing molecular weight and decreasing annealing temperature similarly to the variation of the chain diffusivity in the melt. The process leading to melt memory is thermally activated as the variation ofX_c,thresholdwith temperature follows Arrhenius behavior with high activation energy (ca108 kJ mol⁻¹) that is independent of molecular weight. © 2018 Society of Chemical Industry