Long-form question answering (LFQA) aims at generating in-depth answers to end-user questions, providing relevant information beyond the direct answer. However, existing retrievers are typically optimized towards information that directly targets the question, missing out on such contextual information. Furthermore, there is a lack of training data for relevant context. To this end, we propose and compare different weak supervision techniques to optimize retrieval for contextual information. Experiments demonstrate improvements on the end-to-end QA performance on ASQA, a dataset for long-form question answering. Importantly, as more contextual information is retrieved, we improve the relevant page recall for LFQA by 14.7% and the groundedness of generated long-form answers by 12.5%. Finally, we show that long-form answers often anticipate likely follow-up questions, via experiments on a conversational QA dataset.

Recent years have witnessed the thriving of pretrained Transformer-based language models for understanding semi-structured tables, with several applications, such as Table Question Answering (TableQA).These models are typically trained on joint tables and surrounding natural language text, by linearizing table content into sequences comprising special tokens and cell information. This yields very long sequences which increase system inefficiency, and moreover, simply truncating long sequences results in information loss for downstream tasks. We propose Inner Table Retriever (ITR), a general-purpose approach for handling long tables in TableQA that extracts sub-tables to preserve the most relevant information for a question. We show that ITR can be easily integrated into existing systems to improve their accuracy with up to 1.3-4.8% and achieve state-of-the-art results in two benchmarks, i.e., 63.4% in WikiTableQuestions and 92.1% in WikiSQL. Additionally, we show that ITR makes TableQA systems more robust to reduced model capacity and to different ordering of columns and rows. We make our code available at: https://github.com/amazon-science/robust-tableqa.

Recent open-domain TableQA models are typically implemented as retriever-reader pipelines. The retriever component is usually a variant of the Dense Passage Retriever, which computes the similarities between questions and tables based on a single representation of each. These fixed vectors can be insufficient to capture fine-grained features of potentially very big tables with heterogeneous row/column information. We address this limitation by 1) applying late interaction models which enforce a finer-grained interaction between question and table embeddings at retrieval time. In addition, we 2) incorporate a joint training scheme of the retriever and reader with explicit table-level signals, and 3) embed a binary relevance token as a prefix to the answer generated by the reader, so we can determine at inference time whether the table used to answer the question is reliable and filter accordingly. The combined strategies set a new state-to-the-art performance on two public open-domain TableQA datasets.

Product Question Answering (PQA) systems are key in e-commerce applications as they provide responses to customers’ questions as they shop for products. While existing work on PQA focuses mainly on English, in practice there is need to support multiple customer languages while leveraging product information available in English. To study this practical industrial task, we present xPQA, a large-scale annotated cross-lingual PQA dataset in 12 languages, and report results in (1) candidate ranking, to select the best English candidate containing the information to answer a non-English question; and (2) answer generation, to generate a natural-sounding non-English answer based on the selected English candidate. We evaluate various approaches involving machine translation at runtime or offline, leveraging multilingual pre-trained LMs, and including or excluding xPQA training data. We find that in-domain data is essential as cross-lingual rankers trained on other domains perform poorly on the PQA task, and that translation-based approaches are most effective for candidate ranking while multilingual finetuning works best for answer generation. Still, there remains a significant performance gap between the English and the cross-lingual test sets.

Neural ranking (NR) has become a key component for open-domain question-answering in order to access external knowledge. However, training a good NR model requires substantial amounts of relevance annotations, which is very costly to scale. To address this, a growing body of research works have been proposed to reduce the annotation cost by training the NR model with weak supervision (WS) instead. These works differ in what resources they require and employ a diverse set of WS signals to train the model. Understanding such differences is crucial for choosing the right WS technique. To facilitate this understanding, we provide a structured overview of standard WS signals used for training a NR model. Based on their required resources, we divide them into three main categories: (1) only documents are needed; (2) documents and questions are needed; and (3) documents and question-answer pairs are needed. For every WS signal, we review its general idea and choices. Promising directions are outlined for future research.

Unlike the Open Domain Question Answering (ODQA) setting, the conversational (ODConvQA) domain has received limited attention when it comes to reevaluating baselines for both efficiency and effectiveness. In this paper, we study the State-of-the-Art (SotA) Dense Passage Retrieval (DPR) retriever and Fusion-in-Decoder (FiD) reader pipeline, and show that it significantly underperforms when applied to ODConvQA tasks due to various limitations. We then propose and evaluate strong yet simple and efficient baselines, by introducing a fast reranking component between the retriever and the reader, and by performing targeted finetuning steps. Experiments on two ODConvQA tasks, namely TopiOCQA and OR-QuAC, show that our method improves the SotA results, while reducing reader’s latency by 60%. Finally, we provide new and valuable insights into the development of challenging baselines that serve as a reference for future, more intricate approaches, including those that leverage Large Language Models (LLMs).

We introduce question answering with a cotext in focus, a task that simulates a free interaction with a QA system. The user reads on a screen some information about a topic, and they can follow-up with questions that can be either related or not to the topic; and the answer can be found in the document containing the screen content or from other pages. We call such information context. To study the task, we construct FocusQA, a dataset for answer sentence selection (AS2) with 12,165011unique question/context pairs, and a total of 109,940 answers. To build the dataset, we developed a novel methodology that takes existing questions and pairs them with relevant contexts. To show the benefits of this approach, we present a comparative analysis with a set of questions written by humans after reading the context, showing that our approach greatly helps in eliciting more realistic question/context pairs. Finally, we show that the task poses several challenges for incorporating contextual information. In this respect, we introduce strong baselines for answer sentence selection that outperform the precision of state-of-the-art models for AS2 up to 21.3% absolute points.

In conversational QA, models have to leverage information in previous turns to answer upcoming questions. Current approaches, such as Question Rewriting, struggle to extract relevant information as the conversation unwinds. We introduce the Common Ground (CG), an approach to accumulate conversational information as it emerges and select the relevant information at every turn. We show that CG offers a more efficient and human-like way to exploit conversational information compared to existing approaches, leading to improvements on Open Domain Conversational QA.

It is of great value to answer product questions based on heterogeneous information sources available on web product pages, e.g., semi-structured attributes, text descriptions, user-provided contents, etc. However, these sources have different structures and writing styles, which poses challenges for (1) evidence ranking, (2) source selection, and (3) answer generation. In this paper, we build a benchmark with annotations for both evidence selection and answer generation covering 6 information sources. Based on this benchmark, we conduct a comprehensive study and present a set of best practices. We show that all sources are important and contribute to answering questions. Handling all sources within one single model can produce comparable confidence scores across sources and combining multiple sources for training always helps, even for sources with totally different structures. We further propose a novel data augmentation method to iteratively create training samples for answer generation, which achieves close-to-human performance with only a few thousandannotations. Finally, we perform an in-depth error analysis of model predictions and highlight the challenges for future research.

Product question answering (PQA) aims to automatically address customer questions to improve their online shopping experience. Current research mainly focuses on finding answers from either unstructured text, like product descriptions and user reviews, or structured knowledge bases with pre-defined schemas. Apart from the above two sources, a lot of product information is represented in a semi-structured way, e.g., key-value pairs, lists, tables, json and xml files, etc. These semi-structured data can be a valuable answer source since they are better organized than free text, while being easier to construct than structured knowledge bases. However, little attention has been paid to them. To fill in this blank, here we study how to effectively incorporate semi-structured answer sources for PQA and focus on presenting answers in a natural, fluent sentence. To this end, we present semiPQA: a dataset to benchmark PQA over semi-structured data. It contains 11,243 written questions about json-formatted data covering 320 unique attribute types. Each data point is paired with manually-annotated text that describes its contents, so that we can train a neural answer presenter to present the data in a natural way. We provide baseline results and a deep analysis on the successes and challenges of leveraging semi-structured data for PQA. In general, state-of-the-art neural models can perform remarkably well when dealing with seen attribute types. For unseen attribute types, however, a noticeable drop is observed for both answer presentation and attribute ranking.

We investigate adaptive ensemble weighting for Neural Machine Translation, addressing the case of improving performance on a new and potentially unknown domain without sacrificing performance on the original domain. We adapt sequentially across two Spanish-English and three English-German tasks, comparing unregularized fine-tuning, L2 and Elastic Weight Consolidation. We then report a novel scheme for adaptive NMT ensemble decoding by extending Bayesian Interpolation with source information, and report strong improvements across test domains without access to the domain label.

In the Japanese language different levels of honorific speech are used to convey respect, deference, humility, formality and social distance. In this paper, we present a method for controlling the level of formality of Japanese output in English-to-Japanese neural machine translation (NMT). By using heuristics to identify honorific verb forms, we classify Japanese sentences as being one of three levels of informal, polite, or formal speech in parallel text. The English source side is marked with a feature that identifies the level of honorific speech present in the Japanese target side. We use this parallel text to train an English-Japanese NMT model capable of producing Japanese translations in different honorific speech styles for the same English input sentence.

Two techniques provide the fabric of the Cambridge University Engineering Department’s (CUED) entry to the WMT19 evaluation campaign: elastic weight consolidation (EWC) and different forms of language modelling (LMs). We report substantial gains by fine-tuning very strong baselines on former WMT test sets using a combination of checkpoint averaging and EWC. A sentence-level Transformer LM and a document-level LM based on a modified Transformer architecture yield further gains. As in previous years, we also extract n-gram probabilities from SMT lattices which can be seen as a source-conditioned n-gram LM.

Despite the impressive quality improvements yielded by neural machine translation (NMT) systems, controlling their translation output to adhere to user-provided terminology constraints remains an open problem. We describe our approach to constrained neural decoding based on finite-state machines and multi-stack decoding which supports target-side constraints as well as constraints with corresponding aligned input text spans. We demonstrate the performance of our framework on multiple translation tasks and motivate the need for constrained decoding with attentions as a means of reducing misplacement and duplication when translating user constraints.

We describe a batched beam decoding algorithm for NMT with LMBR n-gram posteriors, showing that LMBR techniques still yield gains on top of the best recently reported results with Transformers. We also discuss acceleration strategies for deployment, and the effect of the beam size and batching on memory and speed.

We explore strategies for incorporating target syntax into Neural Machine Translation. We specifically focus on syntax in ensembles containing multiple sentence representations. We formulate beam search over such ensembles using WFSTs, and describe a delayed SGD update training procedure that is especially effective for long representations like linearized syntax. Our approach gives state-of-the-art performance on a difficult Japanese-English task.

The University of Cambridge submission to the WMT18 news translation task focuses on the combination of diverse models of translation. We compare recurrent, convolutional, and self-attention-based neural models on German-English, English-German, and Chinese-English. Our final system combines all neural models together with a phrase-based SMT system in an MBR-based scheme. We report small but consistent gains on top of strong Transformer ensembles.

We present a novel scheme to combine neural machine translation (NMT) with traditional statistical machine translation (SMT). Our approach borrows ideas from linearised lattice minimum Bayes-risk decoding for SMT. The NMT score is combined with the Bayes-risk of the translation according the SMT lattice. This makes our approach much more flexible than n-best list or lattice rescoring as the neural decoder is not restricted to the SMT search space. We show an efficient and simple way to integrate risk estimation into the NMT decoder which is suitable for word-level as well as subword-unit-level NMT. We test our method on English-German and Japanese-English and report significant gains over lattice rescoring on several data sets for both single and ensembled NMT. The MBR decoder produces entirely new hypotheses far beyond simply rescoring the SMT search space or fixing UNKs in the NMT output.

We compare several language models for the word-ordering task and propose a new bag-to-sequence neural model based on attention-based sequence-to-sequence models. We evaluate the model on a large German WMT data set where it significantly outperforms existing models. We also describe a novel search strategy for LM-based word ordering and report results on the English Penn Treebank. Our best model setup outperforms prior work both in terms of speed and quality.

This paper describes a statistical machine translation system that uses a translation model which is based on bilingual n-grams. When this translation model is log-linearly combined with four specific feature functions, state of the art translations are achieved for Spanish-to-English and English-to-Spanish translation tasks. Some specific results obtained for the EPPS (European Parliament Plenary Sessions) data are presented and discussed. Finally, future research issues are depicted.

In Statistical Machine Translation, the use of reordering for certain language pairs can produce a significant improvement on translation accuracy. However, the search problem is shown to be NP-hard when arbitrary reorderings are allowed. This paper addresses the question of reordering for an Ngram-based SMT approach following two complementary strategies, namely reordered search and tuple unfolding. These strategies interact to improve translation quality in a Chinese to English task. On the one hand, we allow for an Ngram-based decoder (MARIE) to perform a reordered search over the source sentence, while combining a translation tuples Ngram model, a target language model, a word penalty and a word distance model. Interestingly, even though the translation units are learnt sequentially, its reordered search produces an improved translation. On the other hand, we allow for a modification of the translation units that unfolds the tuples, so that shorter units are learnt from a new parallel corpus, where the source sentences are reordered according to the target language. This tuple unfolding technique reduces data sparseness and, when combined with the reordered search, further boosts translation performance. Translation accuracy and efficency results are reported for the IWSLT 2004 Chinese to English task.