This paper presents first successful steps in designing search agents that learn meta-strategies for iterative query refinement in information-seeking tasks. Our approach uses machine reading to guide the selection of refinement terms from aggregated search results. Agents are then empowered with simple but effective search operators to exert fine-grained and transparent control over queries and search results. We develop a novel way of generating synthetic search sessions, which leverages the power of transformer-based language models through (self-)supervised learning. We also present a reinforcement learning agent with dynamically constrained actions that learns interactive search strategies from scratch. Our search agents obtain retrieval and answer quality performance comparable to recent neural methods, using only a traditional term-based BM25 ranking function and interpretable discrete reranking and filtering actions.View details
The predictions of question answering (QA) systems are typically evaluated against manually annotated finite sets of one or more answers. This leads to a coverage limitation that results in underestimating the true performance of systems, and is typically addressed by extending over exact match (EM) with predefined rules or with the token-level F1 measure. In this paper, we present the first systematic conceptual and data-driven analysis to examine the shortcomings of token-level equivalence measures.
To this end, we define the asymmetric notion of answer equivalence (AE), accepting answers that are equivalent to or improve over the reference, and publish over 23k human judgments for candidates produced by multiple QA systems on SQuAD. Through a careful analysis of this data, we reveal and quantify several concrete limitations of the F1 measure, such as a false impression of graduality, or missing dependence on the question.
Since collecting AE annotations for each evaluated model is expensive, we learn a BERT matching (BEM) measure to approximate this task. Being a simpler task than QA, we find BEM to provide significantly better AE approximations than F1, and to more accurately reflect the performance of systems.
Finally, we demonstrate the practical utility of AE and BEM on the concrete application of minimal accurate prediction sets, reducing the number of required answers by up to ×2.6.View details
We release FoolMeTwice (FM2 for short), a large dataset of challenging entailment pairs collected through a fun multi-player game. Gamification encourages adversarial examples, drastically lowering the number of examples that can be solved using "shortcuts" compared to other popular entailment datasets. Players are presented with two tasks. The first task asks the player to write a plausible claim based on the evidence from a Wikipedia page. The second one shows two plausible claims written by other players, one of which is false, and the goal is to identify it before the time runs out. Players "pay" to see clues retrieved from the evidence pool: the more evidence the player needs, the harder the claim. Game-play between motivated players leads to diverse strategies for crafting claims, such as temporal inference and diverting to unrelated evidence, and results in higher quality data for the entailment and evidence retrieval tasks. We open source the dataset and the game code.View details
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, Online (2020), pp. 7422-7435
In additon to the traditional task of getting machines to answer questions, a major research question in question answering is to create interesting, challenging questions that can help systems learn how to answer questions and also reveal which systems are the best at answering questions. We argue that creating a question answering dataset—and the ubiquitous leaderboard that goes with it—closely resembles running a trivia tournament: you write questions, have agents (either humans or machines)
answer the questions, and declare a winner. However, the research community has ignored the decades of hard-learned lessons from decades of the trivia community creating vibrant, fair, and effective question answering competitions. After detailing problems with existing QA datasets, we outline the key lessons—removing ambiguity, discriminating skill, and adjudicating disputes—that can transfer to QA research and how they might be implemented for the QA community.View details
Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing, Association for Computational Linguistics, Beijing, China (2015), pp. 1460-1469
Most existing topic models make the bagof-words assumption that words are generated independently, and so ignore potentially useful information about word order. Previous attempts to use collocations (short sequences of adjacent words) in topic models have either relied on a pipeline approach, restricted attention to bigrams, or resulted in models whose inference does not scale to large corpora. This paper studies how to simultaneously learn both collocations and their topic assignments. We present an efficient reformulation of the Adaptor Grammar-based topical collocation model (AG-colloc) (Johnson, 2010), and develop a point-wise sampling algorithm for posterior inference in this new formulation. We further improve the efficiency of the sampling algorithm by exploiting sparsity and parallelising inference. Experimental results derived in text classification, information retrieval and human evaluation tasks across a range of datasets show that this reformulation scales to hundreds of thousands of documents while maintaining the good performance of the AG-colloc model.View details
No Results Found
We're always looking for more talented, passionate people.