People speaking different kinds of languages search for information in a cross-lingual manner. They tend to ask questions in their language and expect the answer to be in the same language, despite the evidence lying in another language. In this paper, we present our approach for this task of cross-lingual open-domain question-answering. Our proposed method employs a passage reranker, the fusion-in-decoder technique for generation, and a wiki data entity-based post-processing system to tackle the inability to generate entities across all languages. Our end-2-end pipeline shows an improvement of 3 and 4.6 points on F1 and EM metrics respectively, when compared with the baseline CORA model on the XOR-TyDi dataset. We also evaluate the effectiveness of our proposed techniques in the zero-shot setting using the MKQA dataset and show an improvement of 5 points in F1 for high-resource and 3 points improvement for low-resource zero-shot languages. Our team, CMUmQA’s submission in the MIA-Shared task ranked 1st in the constrained setup for the dev and 2nd in the test setting.

In this paper, we present our submission to the DialDoc shared task based on the MultiDoc2Dial dataset. MultiDoc2Dial is a conversational question answering dataset that grounds dialogues in multiple documents. The task involves grounding a user’s query in a document followed by generating an appropriate response. We propose several improvements over the baseline’s retriever-reader architecture to aid in modeling goal-oriented dialogues grounded in multiple documents. Our proposed approach employs sparse representations for passage retrieval, a passage re-ranker, the fusion-in-decoder architecture for generation, and a curriculum learning training paradigm. Our approach shows a 12 point improvement in BLEU score compared to the baseline RAG model.

Code-switched (CS) data is ubiquitous in today’s globalized world, but the dearth of annotated datasets in code-switching poses a significant challenge for learning diverse tasks across different language pairs. Parameter-efficient prompt-tuning approaches conditioned on frozen language models have shown promise for transfer learning in limited-resource setups. In this paper, we propose a novel instance-based prompt composition technique, PRO-CS, for CS tasks that combine language and task knowledge. We compare our approach with prompt-tuning and fine-tuning for code-switched tasks on 10 datasets across 4 language pairs. Our model outperforms the prompt-tuning approach by significant margins across all datasets and outperforms or remains at par with fine-tuning by using just 0.18% of total parameters. We also achieve competitive results when compared with the fine-tuned model in the low-resource cross-lingual and cross-task setting, indicating the effectiveness of our approach to incorporate new code-switched tasks.

Social media sites like Facebook, Twitter, and other microblogging forums have emerged as a platform for people to express their opinions and views on different issues and events. It is often observed that people tend to take a stance; in favor, against or neutral towards a particular topic. The task of assessing the stance taken by the individual became significantly important with the emergence in the usage of online social platforms. Automatic stance detection system understands the user’s stance by analyzing the standalone texts against a target entity. Due to the limited contextual information a single sentence provides, it is challenging to solve this task effectively. In this paper, we introduce a Multi-Task Learning (MTL) based deep neural network architecture for automatically detecting stance present in the code-mixed corpus. We apply our approach on Hindi-English code-mixed corpus against the target entity - “Demonetisation.” Our best model achieved the result with a stance prediction accuracy of 63.2% which is a 4.5% overall accuracy improvement compared to the current supervised classification systems developed using the benchmark dataset for code-mixed data stance detection.

We propose bilingual word embeddings based on word2vec and fastText models (CBOW and Skip-gram) to address the problem of Humor detection in Hindi-English code-mixed tweets in combination with deep learning architectures. We focus on deep learning approaches which are not widely used on code-mixed data and analyzed their performance by experimenting with three different neural network models. We propose convolution neural network (CNN) and bidirectional long-short term memory (biLSTM) (with and without Attention) models which take the generated bilingual embeddings as input. We make use of Twitter data to create bilingual word embeddings. All our proposed architectures outperform the state-of-the-art results, and Attention-based bidirectional LSTM model achieved an accuracy of 73.6% which is an increment of more than 4% compared to the current state-of-the-art results.