{ "id": 229240, "title": "Collection of the most interesting github repos on Question-Answering", "url": "/competitions/coleridgeinitiative-show-us-the-data/discussion/229240", "author_name": "Anaida Shaginian", "post_date": "2021-03-29T06:55:39.115000", "votes": 2, "comment_count": 0, "views": 0, "content": "
    \n

  1. https://github.com/studio-ousia/luke. LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-trained contextualized representation of words and entities based on transformer. It achieves state-of-the-art results on important NLP benchmarks including SQuAD v1.1 (extractive question answering), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), TACRED (relation classification), and Open Entity (entity typing).

    2. \n

  2. https://github.com/zihangdai/xlnet. XLNet is a new unsupervised language representation learning method based on a novel generalized permutation language modeling objective. Additionally, XLNet employs Transformer-XL as the backbone model, exhibiting excellent performance for language tasks involving long context. Overall, XLNet achieves state-of-the-art (SOTA) results on various downstream language tasks including question answering, natural language inference, sentiment analysis, and document ranking.

    3. \n

  3. https://github.com/allenai/bi-att-flow. The original implementation of Bi-directional Attention Flow for Machine Comprehension.

    4. \n

  4. https://github.com/alexa/wqa_tanda. TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection.

    5. \n
", "messages": [ { "id": 1255746, "postDate": "2021-03-29T06:55:39.117Z", "content": "
    \n

  1. https://github.com/studio-ousia/luke. LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-trained contextualized representation of words and entities based on transformer. It achieves state-of-the-art results on important NLP benchmarks including SQuAD v1.1 (extractive question answering), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), TACRED (relation classification), and Open Entity (entity typing).

    2. \n

  2. https://github.com/zihangdai/xlnet. XLNet is a new unsupervised language representation learning method based on a novel generalized permutation language modeling objective. Additionally, XLNet employs Transformer-XL as the backbone model, exhibiting excellent performance for language tasks involving long context. Overall, XLNet achieves state-of-the-art (SOTA) results on various downstream language tasks including question answering, natural language inference, sentiment analysis, and document ranking.

    3. \n

  3. https://github.com/allenai/bi-att-flow. The original implementation of Bi-directional Attention Flow for Machine Comprehension.

    4. \n

  4. https://github.com/alexa/wqa_tanda. TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection.

    5. \n
", "rawMarkdown": "1. https://github.com/studio-ousia/luke. LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-trained contextualized representation of words and entities based on transformer. It achieves state-of-the-art results on important NLP benchmarks including SQuAD v1.1 (extractive question answering), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), TACRED (relation classification), and Open Entity (entity typing).\n\n2. https://github.com/zihangdai/xlnet. XLNet is a new unsupervised language representation learning method based on a novel generalized permutation language modeling objective. Additionally, XLNet employs Transformer-XL as the backbone model, exhibiting excellent performance for language tasks involving long context. Overall, XLNet achieves state-of-the-art (SOTA) results on various downstream language tasks including question answering, natural language inference, sentiment analysis, and document ranking.\n\n3. https://github.com/allenai/bi-att-flow. The original implementation of Bi-directional Attention Flow for Machine Comprehension.\n\n4. https://github.com/alexa/wqa_tanda. TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection.", "votes": 2 } ], "comments": [], "raw_markdown_by_id": { "1255746": "1. https://github.com/studio-ousia/luke. LUKE (Language Understanding with Knowledge-based Embeddings) is a new pre-trained contextualized representation of words and entities based on transformer. It achieves state-of-the-art results on important NLP benchmarks including SQuAD v1.1 (extractive question answering), CoNLL-2003 (named entity recognition), ReCoRD (cloze-style question answering), TACRED (relation classification), and Open Entity (entity typing).\n\n2. https://github.com/zihangdai/xlnet. XLNet is a new unsupervised language representation learning method based on a novel generalized permutation language modeling objective. Additionally, XLNet employs Transformer-XL as the backbone model, exhibiting excellent performance for language tasks involving long context. Overall, XLNet achieves state-of-the-art (SOTA) results on various downstream language tasks including question answering, natural language inference, sentiment analysis, and document ranking.\n\n3. https://github.com/allenai/bi-att-flow. The original implementation of Bi-directional Attention Flow for Machine Comprehension.\n\n4. https://github.com/alexa/wqa_tanda. TANDA: Transfer and Adapt Pre-Trained Transformer Models for Answer Sentence Selection." } }