Add a model trained on wikidata, freebase and dbpedia

README.md

@@ -1,3 +1,43 @@
 ---
 license: mit
 ---
+
+# SRTK Scorer
+
+This model is a trained scorer for [SRTK](https://github.com/happen2me/subgraph-retrieval-toolkit). It is used to compare the similarity between a query and the expansion path at the time of subgraph retrieval.
+
+## Training Information
+
+It is initialized with `roberta-base`. It is trained jointly on the following datasets:
+
+- [WebQSP for Freebase](https://www.microsoft.com/en-us/download/details.aspx?id=52763)
+- [SimpleQuestionsWikidata for Wikidata](https://github.com/askplatypus/wikidata-simplequestions)
+- [SimpleDBpediaQA](https://github.com/castorini/SimpleDBpediaQA)
+
+It achieves a coverage rate of 0.9728 on SimpleQuestionsWikidata (depth 1) 0.8501 on WebQSP test set (depth 2) with a beam width of only 2!
+
+## Usage Example
+
+First install the package:
+
+```bash
+pip install srtk
+```
+
+Then you can retrieve subgraphs with the help of this scorer:
+
+```bash
+srtk retrieve -i data/wikidata-simplequestions/intermediate/scores_test.jsonl \
+    -o artifacts/subgraphs/wikidata-simple-contrast \
+    -e http://localhost:1234/api/endpoint/sparql \
+    --scorer-model-path drt/srtk-scorer \
+    --scorer  --beam-width 2 --max-depth 1 --evaluate
+```
+
+## Limitations
+
+As both SimpleQuestionsWikidata and SimpleDBpediaQA contain only one-hop relations, the model tends to stop at one-hop when you retrieve subgraphs on Wikidata and DBpedia. We will release a updated version of the model that is trained on a more diverse dataset in the future.
+
+## License
+
+MIT

config.json

@@ -0,0 +1 @@
+{"return_dict": true, "output_hidden_states": false, "output_attentions": false, "torchscript": false, "torch_dtype": null, "use_bfloat16": false, "tf_legacy_loss": false, "pruned_heads": {}, "tie_word_embeddings": true, "is_encoder_decoder": false, "is_decoder": false, "cross_attention_hidden_size": null, "add_cross_attention": false, "tie_encoder_decoder": false, "max_length": 20, "min_length": 0, "do_sample": false, "early_stopping": false, "num_beams": 1, "num_beam_groups": 1, "diversity_penalty": 0.0, "temperature": 1.0, "top_k": 50, "top_p": 1.0, "typical_p": 1.0, "repetition_penalty": 1.0, "length_penalty": 1.0, "no_repeat_ngram_size": 0, "encoder_no_repeat_ngram_size": 0, "bad_words_ids": null, "num_return_sequences": 1, "chunk_size_feed_forward": 0, "output_scores": false, "return_dict_in_generate": false, "forced_bos_token_id": null, "forced_eos_token_id": null, "remove_invalid_values": false, "exponential_decay_length_penalty": null, "suppress_tokens": null, "begin_suppress_tokens": null, "architectures": ["RobertaForMaskedLM"], "finetuning_task": null, "id2label": {"0": "LABEL_0", "1": "LABEL_1"}, "label2id": {"LABEL_0": 0, "LABEL_1": 1}, "tokenizer_class": null, "prefix": null, "bos_token_id": 0, "pad_token_id": 1, "eos_token_id": 2, "sep_token_id": null, "decoder_start_token_id": null, "task_specific_params": null, "problem_type": null, "_name_or_path": "roberta-base", "transformers_version": "4.26.0", "model_type": "roberta", "vocab_size": 50265, "hidden_size": 768, "num_hidden_layers": 12, "num_attention_heads": 12, "hidden_act": "gelu", "intermediate_size": 3072, "hidden_dropout_prob": 0.1, "attention_probs_dropout_prob": 0.1, "max_position_embeddings": 514, "type_vocab_size": 1, "initializer_range": 0.02, "layer_norm_eps": 1e-05, "position_embedding_type": "absolute", "use_cache": true, "classifier_dropout": null}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47efaf4afa2de3c4466e4dd6f890b310a6bcd0cb8446905bf16769a703b86a34
+size 498662001

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,16 @@
+{
+  "add_prefix_space": false,
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "errors": "replace",
+  "mask_token": "<mask>",
+  "model_max_length": 512,
+  "name_or_path": "roberta-base",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "tokenizer_class": "RobertaTokenizer",
+  "trim_offsets": true,
+  "unk_token": "<unk>"
+}