{"work":{"id":"a1b36ec8-6f26-40c2-92cc-790c4e8f63bd","openalex_id":null,"doi":null,"arxiv_id":"1410.3916","raw_key":null,"title":"Memory Networks","authors":null,"authors_text":"URL http://arxiv","year":2014,"venue":"cs.AI","abstract":"We describe a new class of learning models called memory networks. Memory networks reason with inference components combined with a long-term memory component; they learn how to use these jointly. The long-term memory can be read and written to, with the goal of using it for prediction. We investigate these models in the context of question answering (QA) where the long-term memory effectively acts as a (dynamic) knowledge base, and the output is a textual response. We evaluate them on a large-scale QA task, and a smaller, but more complex, toy task generated from a simulated world. In the latter, we show the reasoning power of such models by chaining multiple supporting sentences to answer questions that require understanding the intension of verbs.","external_url":"https://arxiv.org/abs/1410.3916","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T13:15:51.673857+00:00","pith_arxiv_id":"1410.3916","created_at":"2026-05-10T18:05:01.876079+00:00","updated_at":"2026-06-05T21:23:00.469572+00:00","title_quality_ok":false,"display_title":"Memory Networks","render_title":"Memory Networks"},"hub":{"state":{"work_id":"a1b36ec8-6f26-40c2-92cc-790c4e8f63bd","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":23,"external_cited_by_count":null,"distinct_field_count":5,"first_pith_cited_at":"2017-10-30T12:41:12+00:00","last_pith_cited_at":"2026-05-18T16:12:52+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-29T14:38:58.442143+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":4},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":3},{"context_polarity":"baseline","n":1},{"context_polarity":"unclear","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}