Continual learning aims to train a model incre-mentally on a sequence of tasks without forgetting previous knowledge. Although continual learning has been widely studied in computer vision, its application to Vision+Language tasks is not that straightforward, as settings can be parameterized in multiple ways according to their input modalities. In this paper, we present a detailed study of how different settings affect performance for Visual Question Answering. We first propose three plausible task formulations and demonstrate their impact on the performance of continual learning algorithms. We break down several factors of task similarity, showing that performance and sensitivity to task order highly depend on the shift of the output distribution. We also investigate the potential of pretrained models and compare the robustness of transformer models with different visual embeddings. Finally, we provide an analysis interpreting model representations and their impact on forgetting. Our results highlight the importance of stabilizing visual representations in deeper layers.

Conditional language models are predominantly trained with maximum likelihood estimation (MLE), giving probability mass to sparsely observed target sequences. While MLE trained models assign high probability to plausible sequences given the context, the model probabilities often do not accurately rank-order generated sequences by quality. This has been empirically observed in beam search decoding as output quality degrading with large beam sizes, and decoding strategies benefiting from heuristics such as length normalization and repetition-blocking. In this work, we introduce sequence likelihood calibration (SLiC) where the likelihood of model generated sequences are calibrated to better align with reference sequences in the model's latent space. With SLiC, decoding heuristics become unnecessary and decoding candidates' quality significantly improves regardless of the decoding method. Furthermore, SLiC shows no sign of diminishing returns with model scale, and presents alternative ways to improve quality with limited training and inference budgets. With SLiC, we exceed or match SOTA results on a wide range of generation tasks spanning abstractive summarization, question generation, abstractive question answering and data-to-text generation, even with modest-sized models.

Indic languages like Hindi and Tamil are underrepresented in the natural language processing (NLP) field compared to languages like English. Due to this underrepresentation, performance on NLP tasks (such as search algorithms) in Indic languages are inferior to their English counterparts. This difference disproportionately affects those who come from lower socioeconomic statuses because they consume the most Internet content in local languages. The goal of this project is to build an NLP model that performs better than pre-existing models for the task of extractive question-answering (QA) on a public dataset in Hindi and Tamil. Extractive QA is an NLP task where answers to questions are extracted from a corresponding body of text. To build the best solution, we used three different models. The first model is an unmodified cross-lingual version of the NLP model RoBERTa, known as XLM-RoBERTa, that is pretrained on 100 languages. The second model is based on the pretrained RoBERTa model with an extra classification head for the question answering, but we used a custom Indic tokenizer, then optimized hyperparameters and fine tuned on the Indic dataset. The third model is based on XLM-RoBERTa, but with extra finetuning and training on the Indic dataset. We hypothesize the third model will perform best because of the variety of languages the XLM-RoBERTa model has been pretrained on and the additional finetuning on the Indic dataset. This hypothesis was proven wrong because the paired RoBERTa models performed the best as the training data used was most specific to the task performed as opposed to the XLM-RoBERTa models which had much data that was not in either Hindi or Tamil.

Much recent research on information retrieval has focused on how to transfer from one task (typically with abundant supervised data) to various other tasks where supervision is limited, with the implicit assumption that it is possible to generalize from one task to all the rest. However, this overlooks the fact that there are many diverse and unique retrieval tasks, each targeting different search intents, queries, and search domains. In this paper, we suggest to work on Few-shot Dense Retrieval, a setting where each task comes with a short description and a few examples. Surprisingly, LLM prompting with no more than 8 examples allows dual encoders to outperform heavily engineered models trained on MS MARCO like ColBERT v2 (Santhanam et al., 2022) by more than 1.2 nDCG on average on 11 retrieval sets. Further training standard-size re-rankers using the same generated data yields another 5.0 point nDCG improvement. Our studies determine that query generation can be far more effective than previously observed, especially when a small amount of task-specific knowledge is given. Recently, major progress has been made on neural retrieval models such as dual encoders, which can retrieve knowledge from a large collection of documents containing millions to billions of passages (Yih et al., 2011; Lee et al., 2019; Karpukhin et al., 2020). However, Thakur et al. (2021) recently proposed the BEIR heterogeneous retrieval benchmark, and showed that it is still difficult for neural retrievers to perform well on a wide variety of retrieval tasks that lack dedicated training data. Thus, previous approaches focus on transferring knowledge from question answering (QA) datasets such as MS MARCO (Nguyen et al., 2016). To best transfer from QA datasets, expressive retrievers are developed that allow fine-grained token-level interaction such as ColBERT (Khattab & Zaharia, 2020; Santhanam et al., 2022) and SPLADE (Formal et al., 2021) but with higher inference cost.

Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text. Existing methods typically require three steps: (1) decision making based on entailment reasoning; (2) span extraction if required by the above decision; (3) question rephrasing based on the extracted span. However, for nearly all these methods, the span extraction and question rephrasing steps cannot fully exploit the fine-grained entailment reasoning information in decision making step because of their relative independence, which will further enlarge the information gap between decision making and question phrasing. Thus, to tackle this problem, we propose a novel end-to-end framework for conversational machine reading comprehension based on shared parameter mechanism, called entailment reasoning T5 (ET5). Despite the lightweight of our proposed framework, experimental results show that the proposed ET5 achieves new state-of-the-art results on the ShARC leaderboard with the BLEU-4 score of 55.2. Our model and code are publicly available at https://github.com/Yottaxx/ET5.

Most domain adaptation methods for machine reading comprehension (MRC) use a pre-trained question-answer (QA) construction model to generate pseudo QA pairs for MRC transfer. Such a process will inevitably introduce mismatched pairs (i.e., noisy correspondence) due to i) the unavailable QA pairs in target documents, and ii) the domain shift during applying the QA construction model to the target domain. Undoubtedly, the noisy correspondence will degenerate the performance of MRC, which however is neglected by existing works. To solve such an untouched problem, we propose to construct QA pairs by additionally using the dialogue related to the documents, as well as a new domain adaptation method for MRC. Specifically, we propose Robust Domain Adaptation for Machine Reading Comprehension (RMRC) method which consists of an answer extractor (AE), a question selector (QS), and an MRC model. Specifically, RMRC filters out the irrelevant answers by estimating the correlation to the document via the AE, and extracts the questions by fusing the candidate questions in multiple rounds of dialogue chats via the QS. With the extracted QA pairs, MRC is fine-tuned and provides the feedback to optimize the QS through a novel reinforced self-training method. Thanks to the optimization of the QS, our method will greatly alleviate the noisy correspondence problem caused by the domain shift. To the best of our knowledge, this could be the first study to reveal the influence of noisy correspondence in domain adaptation MRC models and show a feasible way to achieve robustness to mismatched pairs. Extensive experiments on three datasets demonstrate the effectiveness of our method.

Automated question generation is an important approach to enable personalisation of English comprehension assessment. Recently, transformer-based pretrained language models have demonstrated the ability to produce appropriate questions from a context paragraph. Typically, these systems are evaluated against a reference set of manually generated questions using n-gram based metrics, or manual qualitative assessment. Here, we focus on a fully automated multiple-choice question generation (MCQG) system where both the question and possible answers must be generated from the context paragraph. Applying n-gram based approaches is challenging for this form of system as the reference set is unlikely to capture the full range of possible questions and answer options. Conversely manual assessment scales poorly and is expensive for MCQG system development. In this work, we propose a set of performance criteria that assess different aspects of the generated multiple-choice questions of interest. These qualities include: grammatical correctness, answerability, diversity and complexity. Initial systems for each of these metrics are described, and individually evaluated on standard multiple-choice reading comprehension corpora.

Conversational question--answer generation is a task that automatically generates a large-scale conversational question answering dataset based on input passages. In this paper, we introduce a novel framework that extracts question-worthy phrases from a passage and then generates corresponding questions considering previous conversations. In particular, our framework revises the extracted answers after generating questions so that answers exactly match paired questions. Experimental results show that our simple answer revision approach leads to significant improvement in the quality of synthetic data. Moreover, we prove that our framework can be effectively utilized for domain adaptation of conversational question answering.

In this paper, we present a system to showcase the capabilities of the latest state-of-the-art retrieval augmented generation models trained on knowledge-intensive language tasks, such as slot filling, open domain question answering, dialogue, and fact-checking. Moreover, given a user query, we show how the output from these different models can be combined to cross-examine the outputs of each other. Particularly, we show how accuracy in dialogue can be improved using the question answering model. We are also releasing all models used in the demo as a contribution of this paper. A short video demonstrating the Figure 1: KGI: System Architecture system is available at https://ibm.box.com/

Deep learning transformers have drastically improved systems that automatically answer questions in natural language. However, different questions demand different answering techniques; here we propose, build and validate an architecture that integrates different modules to answer two distinct kinds of queries. Our architecture takes a free-form natural language text and classifies it to send it either to a Neural Question Answering Reasoner or a Natural Language parser to SQL. We implemented a complete system for the Portuguese language, using some of the main tools available for the language and translating training and testing datasets. Experiments show that our system selects the appropriate answering method with high accuracy (over 99\%), thus validating a modular question answering strategy.