Transformer-based pre-trained models, such as BERT, have achieved remarkable results on machine reading comprehension. However, due to the constraint of encoding length (e.g., 512 WordPiece tokens), a long document is usually split into multiple chun
ks that are independently read. It results in the reading field being limited to individual chunks without information collaboration for long document machine reading comprehension. To address this problem, we propose RoR, a read-over-read method, which expands the reading field from chunk to document. Specifically, RoR includes a chunk reader and a document reader. The former first predicts a set of regional answers for each chunk, which are then compacted into a highly-condensed version of the original document, guaranteeing to be encoded once. The latter further predicts the global answers from this condensed document. Eventually, a voting strategy is utilized to aggregate and rerank the regional and global answers for final prediction. Extensive experiments on two benchmarks QuAC and TriviaQA demonstrate the effectiveness of RoR for long document reading. Notably, RoR ranks 1st place on the QuAC leaderboard (https://quac.ai/) at the time of submission (May 17th, 2021).
Generative language models trained on large, diverse corpora can answer questions about a passage by generating the most likely continuation of the passage followed by a question/answer pair. However, accuracy rates vary depending on the type of ques
tion asked. In this paper we keep the passage fixed, and test with a wide variety of question types, exploring the strengths and weaknesses of the GPT-3 language model. We provide the passage and test questions as a challenge set for other language models.
Existing sarcasm detection systems focus on exploiting linguistic markers, context, or user-level priors. However, social studies suggest that the relationship between the author and the audience can be equally relevant for the sarcasm usage and inte
rpretation. In this work, we propose a framework jointly leveraging (1) a user context from their historical tweets together with (2) the social information from a user's neighborhood in an interaction graph, to contextualize the interpretation of the post. We distinguish between perceived and self-reported sarcasm identification. We use graph attention networks (GAT) over users and tweets in a conversation thread, combined with various dense user history representations. Apart from achieving state-of-the-art results on the recently published dataset of 19k Twitter users with 30K labeled tweets, adding 10M unlabeled tweets as context, our experiments indicate that the graph network contributes to interpreting the sarcastic intentions of the author more than to predicting the sarcasm perception by others.
Knowledge Base Question Answering (KBQA) is to answer natural language questions posed over knowledge bases (KBs). This paper targets at empowering the IR-based KBQA models with the ability of numerical reasoning for answering ordinal constrained que
stions. A major challenge is the lack of explicit annotations about numerical properties. To address this challenge, we propose a pretraining numerical reasoning model consisting of NumGNN and NumTransformer, guided by explicit self-supervision signals. The two modules are pretrained to encode the magnitude and ordinal properties of numbers respectively and can serve as model-agnostic plugins for any IR-based KBQA model to enhance its numerical reasoning ability. Extensive experiments on two KBQA benchmarks verify the effectiveness of our method to enhance the numerical reasoning ability for IR-based KBQA models.
Variational autoencoders have been studied as a promising approach to model one-to-many mappings from context to response in chat response generation. However, they often fail to learn proper mappings. One of the reasons for this failure is the discr
epancy between a response and a latent variable sampled from an approximated distribution in training. Inappropriately sampled latent variables hinder models from constructing a modulated latent space. As a result, the models stop handling uncertainty in conversations. To resolve that, we propose speculative sampling of latent variables. Our method chooses the most probable one from redundantly sampled latent variables for tying up the variable with a given response. We confirm the efficacy of our method in response generation with massive dialogue data constructed from Twitter posts.
Although showing promising values to downstream applications, generating question and answer together is under-explored. In this paper, we introduce a novel task that targets question-answer pair generation from visual images. It requires not only ge
nerating diverse question-answer pairs but also keeping the consistency of them. We study different generation paradigms for this task and propose three models: the pipeline model, the joint model, and the sequential model. We integrate variational inference into these models to achieve diversity and consistency. We also propose region representation scaling and attention alignment to improve the consistency further. We finally devise an evaluator as a quantitative metric for consistency. We validate our approach on two benchmarks, VQA2.0 and Visual-7w, by automatically and manually evaluating diversity and consistency. Experimental results show the effectiveness of our models: they can generate diverse or consistent pairs. Moreover, this task can be used to improve visual question generation and visual question answering.
Word meaning is notoriously difficult to capture, both synchronically and diachronically. In this paper, we describe the creation of the largest resource of graded contextualized, diachronic word meaning annotation in four different languages, based
on 100,000 human semantic proximity judgments. We describe in detail the multi-round incremental annotation process, the choice for a clustering algorithm to group usages into senses, and possible -- diachronic and synchronic -- uses for this dataset.
Numerical reasoning skills are essential for complex question answering (CQA) over text. It requires opertaions including counting, comparison, addition and subtraction. A successful approach to CQA on text, Neural Module Networks (NMNs), follows the
programmer-interpreter paradigm and leverages specialised modules to perform compositional reasoning. However, the NMNs framework does not consider the relationship between numbers and entities in both questions and paragraphs. We propose effective techniques to improve NMNs' numerical reasoning capabilities by making the interpreter question-aware and capturing the relationship between entities and numbers. On the same subset of the DROP dataset for CQA on text, experimental results show that our additions outperform the original NMNs by 3.0 points for the overall F1 score.
Large language models have shown promising results in zero-shot settings. For example, they can perform multiple choice tasks simply by conditioning on a question and selecting the answer with the highest probability. However, ranking by string proba
bility can be problematic due to surface form competition---wherein different surface forms compete for probability mass, even if they represent the same underlying concept in a given context, e.g. computer'' and PC.'' Since probability mass is finite, this lowers the probability of the correct answer, due to competition from other strings that are valid answers (but not one of the multiple choice options). We introduce Domain Conditional Pointwise Mutual Information, an alternative scoring function that directly compensates for surface form competition by simply reweighing each option according to its a priori likelihood within the context of a specific task. It achieves consistent gains in zero-shot performance over both calibrated and uncalibrated scoring functions on all GPT-2 and GPT-3 models on a variety of multiple choice datasets.
This paper introduces a long-range multiple-choice Question Answering (QA) dataset, based on full-length fiction book texts. The questions are formulated as 10-way multiple-choice questions, where the task is to select the correct character name give
n a character description, or vice-versa. Each character description is formulated in natural text and often contains information from several sections throughout the book. We provide 20,000 questions created from 10,000 manually annotated descriptions of characters from 177 books containing 152,917 words on average. We address the current discourse regarding dataset bias and leakage by a simple anonymization procedure, which in turn enables interesting probing possibilities. Finally, we show that suitable baseline algorithms perform very poorly on this task, with the book size itself making it non-trivial to attempt a Transformer-based QA solution. This leaves ample room for future improvement, and hints at the need for a completely different type of solution.
