International Business Machines Corporation

Guy Feigenblat

Haggai Roitman

David Konopnicki

Odellia Boni

Roee Shraga

Sachindra Joshi

Mustafa Canim

Doron Cohen

Chulaka Gunasekara

Benjamin Sznajder

Yosi Mass

Bar Weiner

Aaron K Baughman

Jatin Ganhotra

Shai Erera

Sai Krishna Reddy Gudimetla

Nicholas Michael Wilkin

Edward Moroshko

In an approach to improve abstract summarization with question and answer rewards embodiments generate, by a question and answer generator, questions and answers corresponding to a generated summary. Further, embodiments evaluate received answers for the generated questions by analyzing received answers associated with the generated summary against answers received for an original summary, and calculate a reward based on the similarity between answers associated with generated summary and the original summary. Additionally, embodiments update the generation model by applying the calculated reward to further train the summary generation model.

Enhancing natural language processing accuracy in computer systems

An example system includes a processor to receive a summary of a conversation to be generated. The processor can input the summary into a trained summary-grounded conversation generator. The processor can receive a generated conversation from the trained summary-grounded conversation generator.

Conversation generation using summary-grounded conversation generators

A processor may transcribe an electronic representation of a dialogue. The processor may identify one or more question-answer pairs from the electronic representation. The processor may generate based upon the one or more identified question-answer pairs a summary of the dialogue. The processor may display the summary of the dialogue to a user.

Summary generation guided by pre-defined queries

A system and a computer-implemented method for ranking tabular data entities by likelihood of comprising answers for (natural language) queries, based on multimodal descriptions of the tabular data entities, comprising separate representations, which represent different aspects of the tabular data entities. The ranking is based on joint representations, generated from the query representation and separate representations of the tabular data entities' aspects, using gated multimodal units. The computer-implemented method may be used for applications such as web searches, data aggregation, and research tasks.

Method and system for table retrieval using multimodal deep co-learning with helper query-dependent and query-independent relevance labels

Multimodal table encoding, including: Receiving an electronic document that contains a table. The table includes multiple rows, multiple columns, and a schema comprising column labels or row labels. The electronic document includes a description of the table which is located externally to the table. Next, operating separate machine learning encoders to separately encode the description, schema, each of the rows, and each of the columns of the table, respectively. The schema, the rows, and the columns are encoded together with end-of-column tokens and end-of-row tokens that mark an end of each column and row, respectively. Then, applying a machine learning gating mechanism to the encoded description, encoded schema, encoded rows, and encoded columns, to produce a fused encoding of the table, wherein the fused encoding is representative of both a structure of the table and a content of the table.

Multimodal table encoding for information retrieval systems

An embodiment calculates a point of view (POV) value for a subportion of an item of media content, including evaluating user inputs related to an automatically detected POV of the subportion of the item. The embodiment also calculates a non-factual cost for the subportion of the item indicative of an amount of the subportion of the item that lacks support in a fact-based corpora. The embodiment also performs a cascaded summarization process comprising generating a summary of the item using the subportion of the item and a summarization technique, analyzing the summary using a fact-checking algorithm to determine whether the summary satisfies a factual score threshold, and performing a next iteration of the cascaded summarization process while the summary fails to satisfy the factual score threshold. The embodiment also communicates a summary satisfying the factual score threshold to a user device.

Cascaded fact-based summarization

Ad-hoc table retrieval, including: Representing each of a plurality of tables as a multi-field text document in which: different modalities of the table are represented as separate fields, and a concatenation of all the modalities is represented as a separate, auxiliary field. Receiving a query. Executing the query on the multi-field text documents, to retrieve a list of preliminarily-ranked candidate tables out of the plurality of tables. Calculating an intrinsic table similarity score for each of the candidate tables, based on the query and the auxiliary field. Calculating an extrinsic table similarity score for each of the candidate tables, based on a cluster hypothesis of the candidate tables. Combining: the preliminary rankings, the intrinsic table similarity scores, and the extrinsic table similarity scores, to re-rank the candidate tables.

Table indexing and retrieval using intrinsic and extrinsic table similarity measures

An embodiment for predicting a performance of a query in retrieving multifield documents is provided. The embodiment may include receiving a query from a user. The embodiment may also include retrieving a list of multifield documents from a corpus of documents in response to the query. The embodiment may further include generating a pseudo-effective (PE) reference-list for each field in the corpus of documents. The embodiment may also include executing one or more existing query performance prediction (QPP) methods on the retrieved list and each generated PE reference-list. The embodiment may further include deriving one or more extended QPP methods. The embodiment may also include estimating a performance of the query in obtaining the retrieved list of multifield documents based on the one or more extended QPP methods.

Query performance prediction for multifield document retrieval

In a computerized information retrieval system: executing a search based on a query, to retrieve a set of tables ranked according to their relevancy to the query, wherein each of the tables includes one or more columns; selecting, from the retrieved tables, a predefined number of highest-ranking tables; scoring each column in the highest-ranking tables using a link analysis algorithm, and selecting, from the scored columns, a predefined number of highest-scoring columns; scoring terms contained within each of the highest-scoring columns, and selecting, from the scored terms, a predefined number of highest-scoring terms; re-ranking the highest-ranking tables by using the highest-scoring terms as pseudo relevance feedback that expands the query; and providing, as a response to the query, at least one of: the re-ranked tables, ordered according to the re-ranking, and data contained in at least one of the re-ranked tables, wherein the data are ordered according to the re-ranking.

Column-based query expansion for table retrieval

Automated keyphrase extraction from a digital text document. A pool of candidate keyphrases of the digital text document is created. A cross-entropy method is then employed to compute a set of output keyphrases out of the pool of candidate keyphrases, by iteratively optimizing an objective function that is configured to cause the set of output keyphrases to be descriptive of one or more main topics discussed in the digital text document. The set of output keyphrases may be used for at least one of: text summarization, text categorization, opinion mining, and document indexing.

Automatic keyphrase extraction from text using the cross-entropy method

A method, computer system, and computer program product for generating a multi-document summary is provided. The embodiment may include receiving a query statement, one or more documents, one or more summary constraints, and quality goals. The embodiment may include identifying one or more keywords within the query statement. The embodiment may include performing a sentence selection from the one or more documents based on the one or more identified keywords. The embodiment may include generating a plurality of candidate summaries of the one or more documents based on the performed sentence selection, the goals, and a cross entropy method. The embodiment may include calculating a quality score for each of the plurality of generated candidate summaries using a plurality of quality features. The embodiment may include selecting a candidate summary from the plurality of generated candidate summaries with the highest calculated quality score that also satisfies a quality score threshold.

Extractive query-focused multi-document summarization

Embodiments of the present systems and methods may provide techniques that provide improved information retrieval. For example, a method may comprise receiving, at the computer system, a query to retrieve a document from a corpus of documents, retrieving, at the computer system, a plurality of documents from the corpus of documents using a plurality of retrieval methods, each retrieval method generating a ranked list of retrieved documents and a score for each document, fusing, at the computer system, the generated ranked list of retrieved documents to form an aggregated ranked list of retrieved documents by re-scoring, at the computer system, the plurality of documents according to its passage scores, with respect to the query and associating, at the computer system, a given document and its maximal passage using relevance information induced from the plurality of ranked lists.

Utilizing passages in fusion-based document retrieval

A method comprising receiving digital documents, a query statement, and a summary length constraint; identifying, for each of said digital documents, a sentence subset, based, at least in part, on said query statement, a modified version of said summary length constraint, and a first set of quality objectives, generating, for each of said sentence subsets, a random forest representation; iteratively (i) sampling, from each of said random forest representations, a plurality of tokens to create a corresponding candidate document summary, based, at least in part, on weights assigned to each of said tokens, (ii) assigning a quality ranking to said candidate document summary, based, at least in part, on said first set of quality objectives and a second set of quality objectives, and (iii) adjusting said weights, based, at least in part, on said quality rankings; and outputting a highest ranking said candidate document as a compressed summary.

Context-aware sentence compression

Embodiments may provide automated summarization of documents, such as scientific documents by using a prior distribution on logical sections learnt from a corpus of human authored summaries. For example, a method of document summarization may comprise receiving, at the computer system, a document and segmenting the document into a plurality of sentences, identifying, at the computer system, sections in the document and aligning each sentence in the document to a section logical role, and summarizing, at the computer system, the document using a probability distribution.

Unsupervised attention based scientific document summarization

A system for generating a multi-modal summary of a digital document, comprising a processor adapted for: extracting from the document a plurality of graphical elements; generating a set of textual descriptions, each generated for one of the graphical elements and associated therewith; selecting, from the set of textual descriptions and a set of text fragments extracted from the document, a set of representative elements having a highest score computed by applying thereto a score function, where a set of representative elements' score is indicative of a degree by which the set of representative elements represents the document; for each representative element of the set of representative elements, where the element is a textual description of a graphical element of the plurality of graphical elements, replacing the element with the graphical element associated therewith; and

Growing community of inventors

Givataym, Israel

Guy Feigenblat