# US 11,308,283 B2 · Lightweight tagging for disjoint entities > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,283 B2 - Document ID: US11308283B2 - Status: Granted - Kind: B2 - Application number: 16/777,426 - Filed: 2020-01-30 - Published: 2021-08-05 - Granted: 2022-04-19 - Earliest claimed: 2020-01-30 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Diwakar Mahajan; Ananya Aniruddha Poddar; Bharath Dandala; Ching-Huei Tsou - Web page: https://patentgrep.com/patent/US11308283B2 ## CPC - G06F 40/295: Named entity recognition - G06F 40/169: Annotation, e.g. comment data or footnotes - G06F 40/211: Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06N 3/045: Combinations of networks - G06N 3/08: Learning methods - G06N 3/09: Supervised learning - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Text data including at least named entities can be received. From the named entities, continuous entities, overlapping entities and disjoint entities can be identified. The overlapping entities can be transformed into continuous entities. The continuous entities, the transformed entities and the disjoint entities can be encoded. The encoded entities can be input to a machine learning language model to train the machine learning model to predict candidate entities. The predicted entities can be decoded to reconstruct the predicted entities. ## Claims ### Claim 1 A computer-implemented method comprising: receiving text data including at least named entities; identifying from the named entities, continuous entities, overlapping entities and disjoint entities; transforming the overlapping entities to continuous entities; encoding the continuous entities, the transformed entities and the disjoint entities; inputting the encoded entities to a machine learning language model to predict candidate entities; and decoding the predicted entities to reconstruct the predicted entities, wherein the encoding uses a DBIO encoding scheme, wherein B and I tags are used to label tokens belonging to the continuous entities, DB and DI tags are used to label the disjoint entities, and O is used to label tokens outside of continuous entities and disjoint entities, wherein the decoding includes determining whether an entity has a DB tag, and responsive to determining that the entity has a DB tag, reconstructing the entity as a disjoint entity. ### Claim 2 (depends on 1) The method of claim 1, wherein the transforming the overlapping entities includes identifying a set of entities which have a shared token and merging the set of entities into a continuous entity. ### Claim 3 (depends on 1) The method of claim 1, wherein responsive to determining that the entity does not have a DB tag, determining whether the entity matches a syntactic pattern, responsive to determining that the entity matches the syntactic pattern, applying the syntactic pattern, the applying extracting the overlapping entities. ### Claim 4 (depends on 3) The method of claim 3, wherein responsive to determining that the entity does not match the syntactic pattern, reconstructing a continuous entity. ### Claim 5 (depends on 1) The method of claim 1, further including training the machine learning language model using a training data set including DBIO encoded text data. ### Claim 6 A system comprising: a hardware processor; a memory device coupled with the hardware processor; the hardware processor configured to: receive text data including at least named entities; identify from the named entities, continuous entities, overlapping entities and disjoint entities; transform the overlapping entities to continuous entities; encode the continuous entities, the transformed entities and the disjoint entities; input the encoded entities to a machine learning language model to predict candidate entities; and decode the predicted entities to reconstruct the predicted entities, wherein the hardware processors is configured to use a DBIO encoding scheme to encode, wherein B and I tags are used to label tokens belonging to the continuous entities, DB and DI tags are used to label the disjoint entities, and O is used to label tokens outside of continuous entities and disjoint entities, wherein the DBIO encoding scheme excludes H tags that label head entities. ### Claim 7 (depends on 6) The system of claim 6, wherein the hardware processors is configured to identify a set of entities which have a shared token and merge the set of entities into a continuous entity, to transform the overlapping entities. ### Claim 8 (depends on 6) The system of claim 6, wherein to decode, the hardware processors is configured to determine whether an entity has a DB tag, and responsive to determining that the entity has a DB tag, reconstruct the entity as a disjoint entity. ### Claim 9 (depends on 8) The system of claim 8, wherein responsive to determining that the entity does not have a DB tag, the hardware processors is configured to determine whether the entity matches a syntactic pattern, responsive to determining that the entity matches the syntactic pattern, the hardware processors is configured to apply the syntactic pattern, applying the syntactic pattern extracting the overlapping entities. ### Claim 10 (depends on 9) The system of claim 9, wherein responsive to determining that the entity does not match the syntactic pattern, the hardware processors is configured to reconstruct a continuous entity. ### Claim 11 (depends on 6) The system of claim 6, wherein the hardware processors is further configured to train the machine learning language model using a training data set including DBIO encoded text data. ### Claim 12 A computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a device to cause the device to: receive text data including at least named entities; identify from the named entities, continuous entities, overlapping entities and disjoint entities; transform the overlapping entities to continuous entities; encode the continuous entities, the transformed entities and the disjoint entities; input the encoded entities to a machine learning language model trained using encoded continuous entities, transformed entities and disjoint entities to predict candidate entities; and decode the predicted entities to reconstruct the predicted entities, wherein the device is caused to train the machine learning model using a DBIO encoding scheme, wherein B and I tags are used to label tokens belonging to the continuous entities, DB and DI tags are used to label the disjoint entities, and O is used to label tokens outside of continuous entities and disjoint entities, wherein to decode, the device is caused to determine whether an entity has a DB tag, and responsive to determining that the entity has a DB tag, reconstruct the entity as a disjoint entity. ### Claim 13 (depends on 12) The computer program product of claim 12, wherein the device is caused to identify a set of entities which have a shared token and merge the set of entities into a continuous entity, to transform the overlapping entities. ### Claim 14 (depends on 12) The computer program product of claim 12, wherein responsive to determining that the entity does not have a DB tag, the device is caused to determine whether the entity matches a syntactic pattern, responsive to determining that the entity matches the syntactic pattern, the device is caused to apply the syntactic pattern, applying the syntactic pattern extracting the overlapping entities. ### Claim 15 (depends on 14) The computer program product of claim 14, wherein responsive to determining that the entity does not match the syntactic pattern, the device is caused to reconstruct a continuous entity.