Abstract: Embodiments described herein provide a query autocompletion (QAC) framework at subword level. Specifically, the QAC framework employs a subword encoder that encodes or converts the sequence of input alphabet letters into a sequence of output subwords. The generated subword candidate sequences from the subword encoder is then for the n-gram language model to perform beam search on. For example, as user queries for search engines are in general short, e.g., ranging from 10 to 30 characters. The n-gram language model at subword level may be used for modeling such short contexts and outperforms the traditional language model in both completion accuracy and runtime speed. Furthermore, key computations are performed prior to the runtime to prepare segmentation candidates in support of the subword encoder to generate subword candidate sequences, thus eliminating significant computational overhead.

Abstract: Embodiments described herein provide methods and systems for effectively and efficiently summarizing long documents. A transformer is provided with bottom-up and top-down inference combined to effectively capture long-range dependency. In the bottom-up inference, each token only attends to nearby tokens within a window of a specified size. In the top-down inference, full self-attention is given using units with coarser granularity. The bottom-up-inferred token representations are then updated with the top-down representations, which is achieved with cross-attention between the top and token levels. Multiple levels of top-down representations with increasingly coarser granularity can be used if documents are extremely long.

Abstract: Embodiments described herein provide document summarization systems and methods that utilize fine-tuning of pre-trained abstractive summarization models to produce summaries that more faithfully track the content of the documents. Such abstractive summarization models may be pre-trained using a corpus consisting of pairs of articles and associated summaries. For each article-summary pair, a pseudo label or control code is generated and represents a faithfulness of the summary with respect to the article. The pre-trained model is then fine-tuned based on the article-summary pairs and the corresponding control codes. The resulting fine-tuned models then provide improved faithfulness in document summarization tasks.

Abstract: Embodiments described herein provide a question answering approach that answers a question by generating an executable logical form. First, a ranking model is used to select a set of good logical forms from a pool of logical forms obtained by searching over a knowledge graph. The selected logical forms are good in the sense that they are close to (or exactly match, in some cases) the intents in the question and final desired logical form. Next, a generation model is adopted conditioned on the question as well as the selected logical forms to generate the target logical form and execute it to obtain the final answer. For example, at inference stage, when a question is received, a matching logical form is identified from the question, based on which the final answer can be generated based on the node that is associated with the matching logical form in the knowledge base.

Abstract: Embodiments described herein provide a question answering approach that answers a question by generating an executable logical form. First, a ranking model is used to select a set of good logical forms from a pool of logical forms obtained by searching over a knowledge graph. The selected logical forms are good in the sense that they are close to (or exactly match, in some cases) the intents in the question and final desired logical form. Next, a generation model is adopted conditioned on the question as well as the selected logical forms to generate the target logical form and execute it to obtain the final answer. For example, at inference stage, when a question is received, a matching logical form is identified from the question, based on which the final answer can be generated based on the node that is associated with the matching logical form in the knowledge base.

Abstract: A conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. The conversation engine loads a chatbot configuration that specifies the behavior of a chatbot including the tasks that can be performed by the chatbot, the types of entities relevant to each task, and so on. The conversation may be voice based and use natural language. The conversation engine may load different chatbot configurations to implement different chatbots. The conversation engine receives a conversation engine configuration that specifies the behavior of the conversation engine across chatbots. The system may be a multi-tenant system that allows customization of the chatbots for each tenant.

Abstract: Embodiments described herein provide a fusion-in-decoder (FID) based model (referred to as “PATHID”) for open-domain multi-hop question answering. Specifically, PATHID addresses the gap between the general behavior of the FID model on single-hop and multi-hop question answering, and provides more transparency into the reasoning path. In addition to answer generation, PATHID explicitly models the full reasoning path to resolve the answer with a generative sequence-to-sequence model.

Abstract: Embodiments described herein provide a dense hierarchical retrieval for open-domain question and answering for a corpus of documents using a document-level and passage-level dense retrieval model. Specifically, each document is viewed as a structural collection that has sections, subsections and paragraphs. Each document may be split into short length passages, where a document-level retrieval model and a passage-level retrieval model may be applied to return a smaller set of filtered texts. Top documents may be identified after encoding the question and the documents and determining document relevance scores to the encoded question. Thereafter, a set of top passages are further identified based on encoding of the passages and determining passage relevance scores to the encoded question. The document and passage relevance scores may be used in combination to determine a final retrieval ranking for the documents having the set of top passages.

Abstract: System and methods for identifying a text word from a spoken utterance are provided. An ensemble BPE system that includes a phone BPE system and a character BPE system receives a spoken utterance. Both BPE systems include a multi-level language model (LM) and an acoustic model. The phone BPE system identifies first words from the spoken utterance and determine a first score for each first word. The first words are converted into character sequences. The character BPE model converts the character sequences into second words and determines a second score for each second word. For each word from the first words that matches a word in the second words the first and second scores are combined. The text word is the word with a highest score.

Abstract: Embodiments described herein provide dynamic blocking, a decoding algorithm which enables large-scale pretrained language models to generate high-quality paraphrases in an un-supervised setting. Specifically, in order to obtain an alternative surface form, when the language model emits a token that is present in the source sequence, the language model is prevented from generating the next token that is the same as the subsequent source token in the source sequence at the next time step. In this way, the language model is forced to generate a paraphrased sequence of the input source sequence, but with mostly different wording.

Abstract: A conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. The conversation engine loads a chatbot configuration that specifies the behavior of a chatbot including the tasks that can be performed by the chatbot, the types of entities relevant to each task, and so on. The conversation may be voice based and use natural language. The conversation engine may load different chatbot configurations to implement different chatbots. The conversation engine receives a conversation engine configuration that specifies the behavior of the conversation engine across chatbots. The system may be a multi-tenant system that allows customization of the chatbots for each tenant.

Abstract: A conversation engine performs conversations with users using chatbots customized for performing a set of tasks that can be performed using an online system. The conversation engine loads a chatbot configuration that specifies the behavior of a chatbot including the tasks that can be performed by the chatbot, the types of entities relevant to each task, and so on. The conversation may be voice based and use natural language. The conversation engine may load different chatbot configurations to implement different chatbots. The conversation engine receives a conversation engine configuration that specifies the behavior of the conversation engine across chatbots. The system may be a multi-tenant system that allows customization of the chatbots for each tenant.

Abstract: Embodiments described herein combine both masked reconstruction and predictive coding. Specifically, unlike contrastive learning, the mutual information between past states and future states are directly estimated. The context information can also be directly captured via shifted masked reconstruction—unlike standard masked reconstruction, the target reconstructed observations are shifted slightly towards the future to incorporate more predictability. The estimated mutual information and shifted masked reconstruction loss can then be combined as the loss function to update the neural model.

Abstract: Embodiments described herein provide a query autocompletion (QAC) framework at subword level. Specifically, the QAC framework employs a subword encoder that encodes or converts the sequence of input alphabet letters into a sequence of output subwords. The generated subword candidate sequences from the subword encoder is then for the n-gram language model to perform beam search on. For example, as user queries for search engines are in general short, e.g., ranging from 10 to 30 characters. The n-gram language model at subword level may be used for modeling such short contexts and outperforms the traditional language model in both completion accuracy and runtime speed. Furthermore, key computations are performed prior to the runtime to prepare segmentation candidates in support of the subword encoder to generate subword candidate sequences, thus eliminating significant computational overhead.

Abstract: Embodiments described herein provide a query autocompletion (QAC) framework at subword level. Specifically, the QAC framework employs a subword encoder that encodes or converts the sequence of input alphabet letters into a sequence of output subwords. The generated subword candidate sequences from the subword encoder is then for the n-gram language model to perform beam search on. For example, as user queries for search engines are in general short, e.g., ranging from 10 to 30 characters. The n-gram language model at subword level may be used for modeling such short contexts and outperforms the traditional language model in both completion accuracy and runtime speed. Furthermore, key computations are performed prior to the runtime to prepare segmentation candidates in support of the subword encoder to generate subword candidate sequences, thus eliminating significant computational overhead.

Abstract: A method for training parameters of a first domain adaptation model. The method includes evaluating a cycle consistency objective using a first task specific model associated with a first domain and a second task specific model associated with a second domain, and evaluating one or more first discriminator models to generate a first discriminator objective using the second task specific model. The one or more first discriminator models include a plurality of discriminators corresponding to a plurality of bands that corresponds domain variable ranges of the first and second domains respectively. The method further includes updating, based on the cycle consistency objective and the first discriminator objective, one or more parameters of the first domain adaptation model for adapting representations from the first domain to the second domain.

Abstract: Embodiments described herein provide systems and methods for a partially supervised training model for online action detection. Specifically, the online action detection framework may include two modules that are trained jointly—a Temporal Proposal Generator (TPG) and an Online Action Recognizer (OAR). In the training phase, OAR performs both online per-frame action recognition and start point detection. At the same time, TPG generates class-wise temporal action proposals serving as noisy supervisions for OAR. TPG is then optimized with the video-level annotations. In this way, the online action detection framework can be trained with video-category labels only without pre-annotated segment-level boundary labels.

Abstract: An automatic speech recognition (ASR) system that determines a textual representation of a word from a word spoken in a natural language is provided. The ASR system uses an acoustic model, a language model, and a decoder. When the ASR system receives a spoken word, the acoustic model generates word candidates for the spoken word. The language model determines an n-gram score for each word candidate. The n-gram score includes a base score and a bias score. The bias score is based on a logarithmic probability of the word candidate, where the logarithmic probability is derived using a class-based language model where the words are clustered into non-overlapping clusters according to word statistics. The decoder decodes a textual representation of the spoken word from the word candidates and the corresponding n-gram score for each word candidate.

Abstract: System and methods for identifying a text word from a spoken utterance are provided. An ensemble BPE system that includes a phone BPE system and a character BPE system receives a spoken utterance. Both BPE systems include a multi-level language model (LM) and an acoustic model. The phone BPE system identifies first words from the spoken utterance and determine a first score for each first word. The first words are converted into character sequences. The character BPE model converts the character sequences into second words and determines a second score for each second word. For each word from the first words that matches a word in the second words the first and second scores are combined. The text word is the word with a highest score.

Abstract: A method for training parameters of a first domain adaptation model includes evaluating a cycle consistency objective using a first task specific model associated with a first domain and a second task specific model associated with a second domain. The evaluating the cycle consistency objective is based on one or more first training representations adapted from the first domain to the second domain by a first domain adaptation model and from the second domain to the first domain by a second domain adaptation model, and one or more second training representations adapted from the second domain to the first domain by the second domain adaptation model and from the first domain to the second domain by the first domain adaptation model. The method further includes evaluating a learning objective based on the cycle consistency objective, and updating parameters of the first domain adaptation model based on learning objective.