Existing passage retrieval systems typically adopt a two-stage retrieve-then-rerank pipeline. To obtain an effective reranking model, many prior works have focused on improving the model architectures, such as leveraging powerful pretrained large language models (LLM) and designing better objective functions. However, less attention has been paid to the issue of collecting high-quality training data. In this paper, we propose HYRR, a framework for training robust reranking models. Specifically, we propose a simple but effective approach to select training data using hybrid retrievers. Our experiments show that the rerankers trained with HYRR are robust to different first-stage retrievers. Moreover, evaluations using MS MARCO and BEIR data sets demonstrate our proposed framework effectively generalizes to both supervised and zero-shot retrieval settings.

It has been shown that dual encoders trained on one domain often fail to generalize to other domains for retrieval tasks. One widespread belief is that the bottleneck layer of a dual encoder, where the final score is simply a dot-product between a query vector and a passage vector, is too limited compared to models with fine-grained interactions between the query and the passage. In this paper, we challenge this belief by scaling up the size of the dual encoder model while keeping the bottleneck layer as a single dot-product with a fixed size. With multi-stage training, scaling up the model size brings significant improvement on a variety of retrieval tasks, especially for out-of-domain generalization. We further analyze the impact of the bottleneck layer and demonstrate diminishing improvement when scaling up the embedding size. Experimental results show that our dual encoders, Generalizable T5-based dense Retrievers (GTR), outperform previous sparse and dense retrievers on the BEIR dataset significantly. Most surprisingly, our ablation study finds that GTR is very data efficient, as it only needs 10% of MS Marco supervised data to match the out-of-domain performance of using all supervised data.

State-of-the-art neural models typically encode document-query pairs using cross-attention for re-ranking. To this end, models generally utilize an encoder-only (like BERT) paradigm or an encoder-decoder (like T5) approach. These paradigms, however, are not without flaws, i.e., running the model on all query-document pairs at inference-time incurs a significant computational cost. This paper proposes a new training and inference paradigm for re-ranking. We propose to finetune a pretrained encoder-decoder model using in the form of document to query generation. Subsequently, we show that this encoder-decoder architecture can be decomposed into a decoder-only language model during inference. This results in significant inference time speedups since the decoder-only architecture only needs to learn to interpret static encoder embeddings during inference. Our experiments show that this new paradigm achieves results that are comparable to the more expensive cross-attention ranking approaches while being up to 6.8X faster. We believe this work paves the way for more efficient neural rankers that leverage large pretrained models.

We propose a neural event coreference model in which event coreference is jointly trained with five tasks: trigger detection, entity coreference, anaphoricity determination, realis detection, and argument extraction. To guide the learning of this complex model, we incorporate cross-task consistency constraints into the learning process as soft constraints via designing penalty functions. In addition, we propose the novel idea of viewing entity coreference and event coreference as a single coreference task, which we believe is a step towards a unified model of coreference resolution. The resulting model achieves state-of-the-art results on the KBP 2017 event coreference dataset.

Despite recent promising results on the application of span-based models for event reference interpretation, there is a lack of understanding of what has been improved. We present an empirical analysis of a state-of-the-art span-based event reference systems with the goal of providing the general NLP audience with a better understanding of the state of the art and reference researchers with directions for future research.

In the context of neural passage retrieval, we study three promising techniques: synthetic data generation, negative sampling, and fusion. We systematically investigate how these techniques contribute to the performance of the retrieval system and how they complement each other. We propose a multi-stage framework comprising of pre-training with synthetic data, fine-tuning with labeled data, and negative sampling at both stages. We study six negative sampling strategies and apply them to the fine-tuning stage and, as a noteworthy novelty, to the synthetic data that we use for pre-training. Also, we explore fusion methods that combine negatives from different strategies. We evaluate our system using two passage retrieval tasks for open-domain QA and using MS MARCO. Our experiments show that augmenting the negative contrast in both stages is effective to improve passage retrieval accuracy and, importantly, they also show that synthetic data generation and negative sampling have additive benefits. Moreover, using the fusion of different kinds allows us to reach performance that establishes a new state-of-the-art level in two of the tasks we evaluated.

We present two extensions to a state-of-theart joint model for event coreference resolution, which involve incorporating (1) a supervised topic model for improving trigger detection by providing global context, and (2) a preprocessing module that seeks to improve event coreference by discarding unlikely candidate antecedents of an event mention using discourse contexts computed based on salient entities. The resulting model yields the best results reported to date on the KBP 2017 English and Chinese datasets.

Despite the significant progress on entity coreference resolution observed in recent years, there is a general lack of understanding of what has been improved. We present an empirical analysis of state-of-the-art resolvers with the goal of providing the general NLP audience with a better understanding of the state of the art and coreference researchers with directions for future research.

Argument compatibility is a linguistic condition that is frequently incorporated into modern event coreference resolution systems. If two event mentions have incompatible arguments in any of the argument roles, they cannot be coreferent. On the other hand, if these mentions have compatible arguments, then this may be used as information towards deciding their coreferent status. One of the key challenges in leveraging argument compatibility lies in the paucity of labeled data. In this work, we propose a transfer learning framework for event coreference resolution that utilizes a large amount of unlabeled data to learn argument compatibility of event mentions. In addition, we adopt an interactive inference network based model to better capture the compatible and incompatible relations between the context words of event mentions. Our experiments on the KBP 2017 English dataset confirm the effectiveness of our model in learning argument compatibility, which in turn improves the performance of the overall event coreference model.

While joint models have been developed for many NLP tasks, the vast majority of event coreference resolvers, including the top-performing resolvers competing in the recent TAC KBP 2016 Event Nugget Detection and Coreference task, are pipeline-based, where the propagation of errors from the trigger detection component to the event coreference component is a major performance limiting factor. To address this problem, we propose a model for jointly learning event coreference, trigger detection, and event anaphoricity. Our joint model is novel in its choice of tasks and its features for capturing cross-task interactions. To our knowledge, this is the first attempt to train a mention-ranking model and employ event anaphoricity for event coreference. Our model achieves the best results to date on the KBP 2016 English and Chinese datasets.

Multi-pass sieve approaches have been successfully applied to entity coreference resolution and many other tasks in natural language processing (NLP), owing in part to the ease of designing high-precision rules for these tasks. However, the same is not true for event coreference resolution: typically lying towards the end of the standard information extraction pipeline, an event coreference resolver assumes as input the noisy outputs of its upstream components such as the trigger identification component and the entity coreference resolution component. The difficulty in designing high-precision rules makes it challenging to successfully apply a multi-pass sieve approach to event coreference resolution. In this paper, we investigate this challenge, proposing the first multi-pass sieve approach to event coreference resolution. When evaluated on the version of the KBP 2015 corpus available to the participants of EN Task 2 (Event Nugget Detection and Coreference), our approach achieves an Avg F-score of 40.32%, outperforming the best participating system by 0.67% in Avg F-score.

Event coreference resolution is a challenging problem since it relies on several components of the information extraction pipeline that typically yield noisy outputs. We hypothesize that exploiting the inter-dependencies between these components can significantly improve the performance of an event coreference resolver, and subsequently propose a novel joint inference based event coreference resolver using Markov Logic Networks (MLNs). However, the rich features that are important for this task are typically very hard to explicitly encode as MLN formulas since they significantly increase the size of the MLN, thereby making joint inference and learning infeasible. To address this problem, we propose a novel solution where we implicitly encode rich features into our model by augmenting the MLN distribution with low dimensional unit clauses. Our approach achieves state-of-the-art results on two standard evaluation corpora.