Loading src/SBERT_Model.py +25 −16 Changes for src/SBERT_Model.py: 25 added lines, 16 removed lines. Original line number Diff line number Diff line Loading @@ -128,6 +128,7 @@ class SBERT_Model: plt.savefig(f'{self.name}_histogram.png', bbox_inches='tight') def get_word_importance(self,sentence_pair, mask="[MASK]"): print(f"Getting word importance of {sentence_pair}") nlp = spacy.load("en_core_web_sm") sentence1 = nlp(sentence_pair[0]) sentence2 = nlp(sentence_pair[1]) Loading @@ -139,41 +140,49 @@ class SBERT_Model: for y in range(len(sentence1)): if y == i: masked_sentence.append(mask) masked_word = sentence1[y].text masked_word = sentence1[y] else: masked_sentence.append(sentence1[y].text) masked_sentence = " ".join(masked_sentence) masked_pair = {"masked word": masked_word, "sentence1": masked_sentence, "sentence2": sentence_pair[1]} masked_pair = {"masked word": masked_word, "sentence1": masked_sentence, "sentence2": sentence_pair[1], "masked sentence": 0} masked_pairs.append(masked_pair) for i in range(len(sentence2)): masked_sentence = [] for y in range(len(sentence2)): if y == i: masked_sentence.append(mask) masked_word = sentence2[y].text masked_word = sentence2[y] else: masked_sentence.append(sentence2[y].text) masked_sentence = " ".join(masked_sentence) masked_pair = {"masked word": masked_word, "sentence1": sentence_pair[0], "sentence2": masked_sentence} masked_pair = {"masked word": masked_word, "sentence1": sentence_pair[0], "sentence2": masked_sentence, "masked sentence": 1} masked_pairs.append(masked_pair) scores = [] for masked_pair in masked_pairs: embs = self.get_embeddings([masked_pair["sentence1"], masked_pair["sentence2"]]) scores.append((masked_pair, float(abs(unmasked_similarity - self.get_cosine_scores(embs[0], embs[1]))))) #TODO: Find out more about the words that cause high deviation from unmasked similarity. # sorted_scores = copy.deepcopy(scores) # sorted_scores.sort(key = lambda x: x[1], reverse=True) # print(f"Pair: {sentence_pair}, Gold: {gold}") # for score in sorted_scores: # masked_pair = score[0] # print(f'1. {masked_pair["sentence1"]}\n \ # 2.{masked_pair["sentence2"]}\n \ # Deviation: {score[1]:.3f}, Masked word: {masked_pair["masked word"]}\n') html_output = [] html_output.append('<div class="sentence">\n') token_scores = [] for i, score in enumerate(scores): masked_pair = score[0] html_output.append(f'<div style="background-color: rgba(0, 160, 252, {score[1]:.2f});">{masked_pair["masked word"]}<br>{score[1]:.2f}</div>\n') if masked_pair["masked sentence"]: doc2 = 0 else: doc2 = 1 token_score = {"doc":[sentence1, sentence2][masked_pair["masked sentence"]], "doc2":[sentence1, sentence2][doc2], "word": masked_pair["masked word"].text, "i": masked_pair["masked word"].i, "score": score[1], "sentence_pair": sentence_pair} token_scores.append(token_score) html_output = [] html_output.append('<div class="sentence">\n') for i, score in enumerate(token_scores): s1_words = [s.text for s in score["doc"]] s2_words = [s.text for s in score["doc2"]] token = score["doc"][score["i"]] cos_score = score["score"] if s1_words.count(token.text) and s2_words.count(token.text): both_sentences = True else: both_sentences = False html_output.append(f'<div id="{randrange(0,10000)}_{token.text}_{token.lemma_}_{both_sentences}_{token.pos_}_{token.tag_}_{token.dep_}_{cos_score:.2f}" style="background-color: rgba(0, 160, 252, {cos_score:.2f});">{token.text}<br>{cos_score:.2f}</div>\n') if i == len(sentence1)-1: html_output.append('</div>\n<div class="sentence">\n') html_output.append('</div>\n') Loading Loading
src/SBERT_Model.py +25 −16 Changes for src/SBERT_Model.py: 25 added lines, 16 removed lines. Original line number Diff line number Diff line Loading @@ -128,6 +128,7 @@ class SBERT_Model: plt.savefig(f'{self.name}_histogram.png', bbox_inches='tight') def get_word_importance(self,sentence_pair, mask="[MASK]"): print(f"Getting word importance of {sentence_pair}") nlp = spacy.load("en_core_web_sm") sentence1 = nlp(sentence_pair[0]) sentence2 = nlp(sentence_pair[1]) Loading @@ -139,41 +140,49 @@ class SBERT_Model: for y in range(len(sentence1)): if y == i: masked_sentence.append(mask) masked_word = sentence1[y].text masked_word = sentence1[y] else: masked_sentence.append(sentence1[y].text) masked_sentence = " ".join(masked_sentence) masked_pair = {"masked word": masked_word, "sentence1": masked_sentence, "sentence2": sentence_pair[1]} masked_pair = {"masked word": masked_word, "sentence1": masked_sentence, "sentence2": sentence_pair[1], "masked sentence": 0} masked_pairs.append(masked_pair) for i in range(len(sentence2)): masked_sentence = [] for y in range(len(sentence2)): if y == i: masked_sentence.append(mask) masked_word = sentence2[y].text masked_word = sentence2[y] else: masked_sentence.append(sentence2[y].text) masked_sentence = " ".join(masked_sentence) masked_pair = {"masked word": masked_word, "sentence1": sentence_pair[0], "sentence2": masked_sentence} masked_pair = {"masked word": masked_word, "sentence1": sentence_pair[0], "sentence2": masked_sentence, "masked sentence": 1} masked_pairs.append(masked_pair) scores = [] for masked_pair in masked_pairs: embs = self.get_embeddings([masked_pair["sentence1"], masked_pair["sentence2"]]) scores.append((masked_pair, float(abs(unmasked_similarity - self.get_cosine_scores(embs[0], embs[1]))))) #TODO: Find out more about the words that cause high deviation from unmasked similarity. # sorted_scores = copy.deepcopy(scores) # sorted_scores.sort(key = lambda x: x[1], reverse=True) # print(f"Pair: {sentence_pair}, Gold: {gold}") # for score in sorted_scores: # masked_pair = score[0] # print(f'1. {masked_pair["sentence1"]}\n \ # 2.{masked_pair["sentence2"]}\n \ # Deviation: {score[1]:.3f}, Masked word: {masked_pair["masked word"]}\n') html_output = [] html_output.append('<div class="sentence">\n') token_scores = [] for i, score in enumerate(scores): masked_pair = score[0] html_output.append(f'<div style="background-color: rgba(0, 160, 252, {score[1]:.2f});">{masked_pair["masked word"]}<br>{score[1]:.2f}</div>\n') if masked_pair["masked sentence"]: doc2 = 0 else: doc2 = 1 token_score = {"doc":[sentence1, sentence2][masked_pair["masked sentence"]], "doc2":[sentence1, sentence2][doc2], "word": masked_pair["masked word"].text, "i": masked_pair["masked word"].i, "score": score[1], "sentence_pair": sentence_pair} token_scores.append(token_score) html_output = [] html_output.append('<div class="sentence">\n') for i, score in enumerate(token_scores): s1_words = [s.text for s in score["doc"]] s2_words = [s.text for s in score["doc2"]] token = score["doc"][score["i"]] cos_score = score["score"] if s1_words.count(token.text) and s2_words.count(token.text): both_sentences = True else: both_sentences = False html_output.append(f'<div id="{randrange(0,10000)}_{token.text}_{token.lemma_}_{both_sentences}_{token.pos_}_{token.tag_}_{token.dep_}_{cos_score:.2f}" style="background-color: rgba(0, 160, 252, {cos_score:.2f});">{token.text}<br>{cos_score:.2f}</div>\n') if i == len(sentence1)-1: html_output.append('</div>\n<div class="sentence">\n') html_output.append('</div>\n') Loading